Hindsight Docs

Hindsight Documentation Skill

Complete technical documentation for Hindsight - a biomimetic memory system for AI agents.

When to Use This Skill

Use this skill when you need to:

• Understand Hindsight architecture and core concepts
• Learn about retain/recall/reflect operations
• Configure memory banks and dispositions
• Set up the Hindsight API server (Docker, Kubernetes, pip)
• Integrate with Python/Node.js/Rust SDKs
• Understand retrieval strategies (semantic, BM25, graph, temporal)
• Debug issues or optimize performance
• Review API endpoints and parameters
• Find cookbook examples and recipes

Documentation Structure

All documentation is in references/ organized by category:

references/
├── best-practices.md # START HERE — missions, tags, formats, anti-patterns
├── faq.md            # Common questions and decisions
├── changelog/        # Release history and version changes (index.md + integrations/)
├── openapi.json      # Full OpenAPI spec — endpoint schemas, request/response models
├── developer/
│   ├── api/          # Core operations: retain, recall, reflect, memory banks
│   └── *.md          # Architecture, configuration, deployment, performance
├── sdks/
│   ├── *.md          # Python, Node.js, CLI, embedded
│   └── integrations/ # LiteLLM, AI SDK, OpenClaw, MCP, skills
└── cookbook/
    ├── recipes/      # Usage patterns and examples
    └── applications/ # Full application demos

How to Find Documentation

1. Find Files by Pattern (use Glob tool)

# Core API operations
references/developer/api/*.md

# SDK documentation
references/sdks/*.md
references/sdks/integrations/*.md

# Cookbook examples
references/cookbook/recipes/*.md
references/cookbook/applications/*.md

# Find specific topics
references/**/configuration.md
references/**/*python*.md
references/**/*deployment*.md

2. Search Content (use Grep tool)

# Search for concepts
pattern: "disposition"        # Memory bank configuration
pattern: "graph retrieval"    # Graph-based search
pattern: "helm install"       # Kubernetes deployment
pattern: "document_id"        # Document management
pattern: "HINDSIGHT_API_"     # Environment variables

# Search in specific areas
path: references/developer/api/
pattern: "POST /v1"           # Find API endpoints

path: references/cookbook/
pattern: "def |async def "    # Find Python examples

3. Read Full Documentation (use Read tool)

references/developer/api/retain.md
references/sdks/python.md
references/cookbook/recipes/per-user-memory.md

Start Here: Best Practices

Before reading API docs, read the best practices guide. It covers practical rules for missions, tags, content format, observation scopes, and anti-patterns — the fastest way to integrate correctly.

references/best-practices.md

Key Concepts

• Memory Banks: Isolated memory stores (one per user/agent)
• Retain: Store memories (auto-extracts facts/entities/relationships)
• Recall: Retrieve memories (4 parallel strategies: semantic, BM25, graph, temporal)
• Reflect: Disposition-aware reasoning using memories
• document_id: Groups messages in a conversation (upsert on same ID)
• Dispositions: Skepticism, literalism, empathy traits (1-5) affecting reflect
• Mental Models: Consolidated knowledge synthesized from facts

Notes

• Code examples are inlined from working examples
• Configuration uses HINDSIGHT_API_* environment variables
• Database migrations run automatically on startup
• Multi-bank queries require client-side orchestration
• Use document_id for conversation evolution (same ID = upsert)

---

Auto-generated from hindsight-docs/docs/. Run ./scripts/generate-docs-skill.sh to update.

<PageHero title="Best Practices" subtitle="Practical guidance for agents and developers integrating Hindsight memory into production systems." />

Contents

• Core Concepts — Memory banks, taxonomy, memory types
• Bank Configuration — Missions, dispositions, entity labels
• Retaining Data — Content format, context, document_id, tags, observation scopes
• Recalling Memories — Budget, tag filtering, entity label filtering, include options, query_timestamp
• Reflecting — Recall vs reflect, response_schema, auditing
• Mental Models — When to create, tag strategy, refresh
• Anti-patterns

---

Core Concepts

Memory Banks

A memory bank is an isolated memory store — the unit of separation between users, agents, or contexts. All operations (retain, recall, reflect) target a single bank. Banks do not share data.

• One bank per user is the most common pattern for multi-user applications
• One bank per agent is common for agent-specific long-term memory
• A shared bank with tags can work for cross-user analysis (see Tags)

Banks are auto-created on first use. Configure them before ingesting data to steer behavior.

---

Taxonomy

---

Memory Types

Facts extracted during retain are classified into three types:

Use types filtering in recall to target specific memory types.

---

Bank Configuration

Configure a bank before first use to steer memory behavior for your domain. Misconfigured missions are the single biggest cause of low-quality memories.

Writing Effective Missions

All three missions accept plain language. Be specific about your domain — vague missions produce vague results.

retain_mission

Injected into the fact extraction prompt. Tells the LLM what to extract and what to ignore.

Tips:

• List the fact types you want (preferences, decisions, errors, commitments)
• List what to ignore — this is as important as what to include
• Match the mission to your actual data type (conversations vs documents vs tickets)

observations_mission

Steers what patterns are synthesized during consolidation. Runs after retain.

Identify evolving preferences, recurring patterns, behavioral shifts, and contradictions
with prior knowledge. Focus on durable patterns — not transient states. Highlight when
user behavior contradicts previous observations.

Tips:

• Emphasize "durable patterns" to avoid ephemeral observation noise
• Mention contradiction detection explicitly if you need historical tracking
• Match scope to how often you expect patterns to change

reflect_mission

Sets the agent persona and reasoning frame for reflect operations.

---

Disposition Traits

Dispositions affect reflect only (not recall). Scale 1–5.

Common profiles:

---

Entity Labels

Define a controlled vocabulary for classification. The LLM will extract and normalize values to your defined set.

{
  "entity_labels": [
    {
      "key": "tech_stack",
      "type": "multi-values",
      "values": [
        {"value": "python", "description": "Python programming language"},
        {"value": "typescript", "description": "TypeScript / Node.js"},
        {"value": "react", "description": "React frontend framework"}
      ]
    },
    {
      "key": "priority",
      "type": "value",
      "tag": true,
      "values": [
        {"value": "high", "description": "Urgent or blocking"},
        {"value": "low", "description": "Nice to have"}
      ]
    }
  ]
}

• `type: "value"` — single value per entity (last write wins)
• `type: "multi-values"` — accumulates multiple values
• `tag: true` — extracted label values are also added as tags (enables filtering by entity value)

Use entity labels when you need consistent classification — domain-specific terms, status values, priority levels, engagement types.

---

Retaining Data

Content Format

Pass the richest representation available. Never pre-summarize.

Conversation JSON (preferred):

[
  {"role": "user",      "content": "I'm using React for the frontend.", "timestamp": "2025-06-01T10:30:00Z"},
  {"role": "assistant", "content": "Got it. What state management are you using?"},
  {"role": "user",      "content": "Zustand. We moved away from Redux last quarter."}
]

Why not pre-summarize: The LLM extracts facts, entities, and relationships from structure. A summary like "user uses React and Zustand" loses the temporal reference ("last quarter"), the entity relationship (React↔frontend, Redux↔migration), and the causal context (moved away from).

---

The context Field

High-impact on extraction quality. Always set it. Describes the nature and source of the content.

# Good — specific, descriptive
context="Customer support ticket #12345 from user Alice about a billing discrepancy"
context="Developer's architecture review session for the payments service"
context="User's onboarding form: stated goals, current tools, and team size"
context="Weekly standup notes: blockers, progress, and upcoming tasks"

# Bad — generic, adds no signal
context="some data"
context="conversation"
# Omitted entirely — extraction uses no context

---

The document_id Field

Use for upsert behavior. Same document_id = delete previous version and reprocess.

Rules:

• Use stable, meaningful IDs (session ID, ticket ID, document UUID)
• Always use the same ID for a growing conversation — retain the full conversation with each new message
• Do NOT use random UUIDs per retain call — this creates duplicates

# Good — stable session ID
client.retain(bank_id="user-alice", items=[{
    "content": full_conversation,
    "document_id": f"session-{session_id}",
}])

# Bad — new random ID every call = duplicates
client.retain(bank_id="user-alice", items=[{
    "content": full_conversation,
    "document_id": str(uuid.uuid4()),  # ❌ creates a new document each time
}])

---

The timestamp Field

Set whenever you have temporal context. Enables temporal retrieval strategies.

• ISO 8601 format: "2025-06-01T10:32:00Z"
• For conversations: set to when the conversation started
• Omitting it disables temporal ranking entirely

---

Tags: Naming Conventions

Tags scope visibility. A memory tagged user:alice is only returned for recall/reflect calls that include user:alice in their tags filter (with strict matching).

Standard naming conventions:

Multi-tenant minimum: Every retain for user data must include at least user:<id>. Omitting it makes the memory globally visible.

# Multi-tenant retain — always tag with user ID
items=[{
    "content": conversation,
    "tags": ["user:alice", "session:s_abc", "topic:billing"],
    "document_id": f"session-{session_id}",
}]

---

Metadata Schema

Use for source tracking and downstream linking. Not filterable — use tags for filtering.

# Source tracking
metadata={"source": "slack", "channel": "#engineering", "thread_id": "T123456"}

# Ticket linking
metadata={"ticket_id": "JIRA-123", "priority": "high", "reporter": "alice"}

# Document provenance
metadata={"url": "https://...", "section": "pricing-faq", "version": "2025-Q1"}

Metadata is returned with every recalled memory — use it to link memories back to source systems for UI display, deep-linking, or audit trails.

---

Observation Scopes

Controls which tag combinations get their own observation pass.

Custom scope example (recommended for multi-tenant):

# Observations scoped to: user-level, team-level, and combined
observation_scopes=[
    ["user:alice"],
    ["team:engineering"],
    ["user:alice", "team:engineering"],
]

---

Sync vs Async

Do not retain and recall in the same turn — retain is a write operation and the extracted memories will not be available immediately.

---

Recalling Memories

Budget Selection

Default to mid. Use low for high-frequency agent loops. Reserve high for explicit "deep recall" user-triggered flows.

---

Tag Filtering Modes

Decision guide:

• Shared global knowledge + per-user: tags=["user:alice"], tags_match="any" — returns Alice's memories and untagged global memories
• Fully partitioned (no leakage): tags=["user:alice"], tags_match="any_strict" — Alice's memories only
• Multi-condition AND: tags=["user:alice", "topic:billing"], tags_match="all_strict" — only where both tags present

`tag_groups` for complex filters:

Tag groups use a tree structure with and/or/not compound nodes and {"tags": [...], "match": "..."} leaf nodes.

# Alice's billing memories OR shared billing memories (no user tag)
recall(
    query="...",
    tag_groups=[
        {"or": [
            {"tags": ["user:alice", "topic:billing"], "match": "all_strict"},
            {"and": [
                {"tags": ["topic:billing"], "match": "any_strict"},
                {"not": {"tags": ["user:alice"], "match": "any_strict"}},
            ]},
        ]}
    ]
)

---

include Options

---

types Filtering

---

Filtering by Memory Shape with Entity Labels

When a single bank contains semantically similar memories that serve different purposes (e.g., concise operating rules vs. detailed troubleshooting procedures), ranking alone cannot reliably distinguish them — two memories about "entrypoints" will score similarly regardless of whether one is a one-line rule and the other is a multi-step runbook.

Use entity labels with tag: true to classify facts at retain time and hard-filter at recall time.

1. Define a label group on the bank:

{
  "entity_labels": [
    {
      "key": "memory_type",
      "description": "The type of knowledge: 'rule' for concise operating rules and canonical guidance, 'procedure' for step-by-step technical instructions and troubleshooting notes",
      "type": "value",
      "optional": false,
      "tag": true,
      "values": [
        { "value": "rule",      "description": "Concise operating rule or canonical guidance" },
        { "value": "procedure", "description": "Step-by-step technical instruction or troubleshooting note" }
      ]
    }
  ]
}

2. Retain normally — the LLM classifies each fact automatically and writes memory_type:rule or memory_type:procedure as a tag.

3. Filter at recall time:

# Only rules — procedures are excluded at the database level, not post-filtered
result = client.recall(
    bank_id="my-bank",
    query="which entrypoint should I use?",
    tags=["memory_type:rule"],
    tags_match="any_strict"
)

This is a hard SQL WHERE clause applied across all four retrieval strategies. The unwanted memories never enter the ranking pipeline.

---

query_timestamp

Set for time-sensitive queries. Anchors relative temporal expressions and recency scoring to a specific point in time.

# "What was the team working on in January?"
recall(query="team priorities", query_timestamp="2025-01-31T23:59:59Z")

# Current context (most common)
recall(query="user preferences", query_timestamp=datetime.utcnow().isoformat() + "Z")

---

Reflecting

Recall vs Reflect

---

response_schema

Use when you need structured output for programmatic consumption.

reflect(
    query="What are the user's top 3 technical preferences?",
    response_schema={
        "type": "object",
        "properties": {
            "preferences": {
                "type": "array",
                "items": {"type": "string"},
                "maxItems": 3
            },
            "confidence": {"type": "number", "minimum": 0, "maximum": 1}
        },
        "required": ["preferences", "confidence"]
    }
)
# Returns: result.structured_output["preferences"], result.structured_output["confidence"]

---

Auditing and Debugging

Enable include.facts in production for audit trails. Enable include.tool_calls only during development.

---

Mental Models

Mental models are pre-computed reflect responses stored for common queries. They return instantly and consistently.

When to Create

• Common repeated queries that should return consistent answers
• High-traffic agents that need sub-100ms responses
• User profiles or personas read on every request
• Knowledge summaries reviewed or approved by humans
• Cross-session state that changes slowly (preferences, skills, background)

Tag Strategy

Tags on a mental model filter BOTH which memories are used to build it AND which recall/reflect calls can see it.

# Per-user mental model — uses Alice's memories (all_strict applied automatically during refresh)
create_mental_model(
    bank_id="shared-bank",
    name="Alice's Technical Profile",
    source_query="Summarize Alice's technical background, preferred stack, and current projects",
    tags=["user:alice"],
)

# Global mental model — uses all memories, visible to everyone
create_mental_model(
    bank_id="shared-bank",
    name="Team Engineering Standards",
    source_query="What are the team's agreed engineering standards and conventions?",
    # No tags — reads all memories, visible to all
)

Refresh Strategy

Create narrow, scoped models — one per knowledge dimension. A mental model titled "Everything about the user" is as useful as none.

Model granularity examples for a personal assistant:

• "User Profile" — demographics, preferences, stated goals
• "Current Projects" — active work, deadlines, blockers
• "Technical Stack" — languages, tools, frameworks used
• "Communication Style" — formality preferences, response length preferences

---

Anti-patterns

ag2 Integration Changelog

Changelog for `hindsight-ag2`.

For the source code, see `hindsight-integrations/ag2`.

← Back to main changelog

0.1.2

Improvements

• Improved type-checking support for the AG2 integration by shipping PEP 561 type information. (`d054b884`)

Bug Fixes

• All HTTP requests from the AG2 integration now include an identifying User-Agent header for improved compatibility and observability. (`9372462e`)
• Resolved critical and high-severity security vulnerabilities in dependencies. (`ee4510a7`)

0.1.1

Features

• Added AG2 framework integration for Hindsight. (`73123870`)

import PageHero from '@site/src/components/PageHero';

<PageHero title="Microsoft Agent Framework Changelog" subtitle="Hindsight memory integration for Microsoft Agent Framework." />

← Microsoft Agent Framework integration

0.1.0

Features

• Added Hindsight memory integration for the Microsoft Agent Framework (without MCP).<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/f5a6c300f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f5a6c300f</a>

Bedrock AgentCore Integration Changelog

Changelog for `hindsight-agentcore`.

For the source code, see `hindsight-integrations/agentcore`.

← Back to main changelog

0.1.1

Features

• Added integration so Hindsight can use Bedrock AgentCore Runtime for memory operations.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c91696f5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c91696f5</a>

Improvements

• Improved the AgentCore integration with an async-native client and better task tracking for more reliable runtime behavior.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/b153541e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b153541e</a>

import PageHero from '@site/src/components/PageHero';

<PageHero title="Vercel AI SDK Changelog" subtitle="@vectorize-io/hindsight-ai-sdk — memory integration for Vercel AI SDK." />

← Vercel AI SDK integration

0.5.1

Bug Fixes

• Fixed AI-SDK reflection tool type definitions to match the OpenAPI spec for more reliable integration behavior.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/3d6b3805" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3d6b3805</a>

0.5.0

Bug Fixes

• Improved compatibility with Hindsight Client v0.5.2 to prevent integration mismatches when using the AI SDK.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/bca87412" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bca87412</a>

0.4.20

Features

• Add AI SDK integration for Hindsight. (`7e339e16`)
• Add Deno compatibility for the TypeScript client. (`72c25c97`)

Improvements

• Improve AI SDK tool support to make integrations more capable and reliable. (`d06a0259`)

Bug Fixes

• Security fixes by resolving dependency vulnerabilities affecting the integration. (`b6a4f17c`)

AutoGen Integration Changelog

Changelog for `hindsight-autogen`.

For the source code, see `hindsight-integrations/autogen`.

← Back to main changelog

0.1.3

Improvements

• Autogen integration now defaults to the Cloud backend and adds gated end-to-end testing to improve reliability and test coverage.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/0eb40a7c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0eb40a7c</a>

0.1.2

Bug Fixes

• Ensure all HTTP requests include an identifying User-Agent header for better reliability and service compatibility. (`9372462e`)

0.1.1

Features

• Added AutoGen integration to connect Hindsight with AutoGen-based agent workflows. (`a757765a`)

import PageHero from '@site/src/components/PageHero';

<PageHero title="Vercel Chat SDK Changelog" subtitle="@vectorize-io/hindsight-chat — memory integration for Vercel Chat SDK." />

← Vercel Chat SDK integration

0.4.20

Features

• Added Chat SDK integration to enable persistent memory for chat bots. (`fed987f9`)
• Added Deno compatibility for the TypeScript client. (`72c25c97`)

Bug Fixes

• Resolved security vulnerabilities in dependencies used across integrations. (`b6a4f17c`)

Claude Agent SDK Integration Changelog

Changelog for `hindsight-claude-agent-sdk`.

For the source code, see `hindsight-integrations/claude-agent-sdk`.

← Back to main changelog

0.1.0

Features

• Added Claude Agent SDK integration for Hindsight.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/a933a417c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>a933a417c</a>

import PageHero from '@site/src/components/PageHero';

<PageHero title="Claude Code Changelog" subtitle="hindsight-memory — Hindsight memory plugin for Claude Code." />

← Claude Code integration

0.7.1

Bug Fixes

• Enable knowledge tools by default and keep the MCP server running even when knowledge tools are disabled.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/655435ea" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>655435ea</a>

0.7.0

Improvements

• Claude Code integration now defaults recall types to observations to improve memory recall behavior out of the box.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/4b19a0fb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4b19a0fb</a>

Bug Fixes

• Recall context now labels the “Current time” value as UTC to avoid timezone confusion.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/valda" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@valda</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/3d6c2ba8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>3d6c2ba8</a>
• Windows MCP bootstrap is now idempotent, preventing failures when re-running the setup script.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/ottopichlhoefer" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@ottopichlhoefer</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/80046797" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>80046797</a>

0.6.5

Features

• Added a configurable timeout for MCP requests in the Claude Code integration.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/rsaulo" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@rsaulo</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/55ef7067" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>55ef7067</a>

0.6.4

Bug Fixes

• Fixed Claude Code recall parameter naming to avoid failures when limiting results.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/offendingcommit" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@offendingcommit</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/909a4fd4" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>909a4fd4</a>
• Improved page retrieval reliability by returning full page content and handling oversized tool results.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/b2a693ab" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b2a693ab</a>
• Corrected the agent knowledge page list tool to fetch metadata-only details, preventing incorrect or overly large responses.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/cdbartholomew" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@cdbartholomew</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/6c6ee73c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6c6ee73c</a>

0.6.3

Features

• Adds explicit directory-to-bank mapping and better support for Git worktrees when using the claude-code integration.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/691c65ac" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>691c65ac</a>

0.6.2

Bug Fixes

• Fixes Claude Code integration setup by bootstrapping required Python dependencies in an isolated virtual environment under the plugin data directory.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/012c100e" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>012c100e</a>

0.6.1

Features

• Claude Code’s create-agent skill now supports and understands SDA project layouts when generating agents.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/0231094d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0231094d</a>

0.6.0

Features

• Added Claude Code knowledge tools backed by a Python MCP server, enabling the integration to read/write and use Hindsight knowledge more directly.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/6c55dbde" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6c55dbde</a>
• Introduced subagents and a new “create-agent” skill to help users create and manage agent configurations/workflows within Claude Code.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/1b9d6d91" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1b9d6d91</a>

0.4.0

Features

• Allows recalling memories from additional banks alongside the primary bank for broader context retrieval.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/starbit-biostar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@starbit-biostar</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/cba2b0d8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>cba2b0d8</a>

Improvements

• Adds a \{user_id\} template variable for retainTags to better organize memories by user.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/soichisumi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@soichisumi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/9181c9a2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9181c9a2</a>

Bug Fixes

• Fixes transcript parsing when tool results include list-style content, preventing recall/retain from failing on some sessions.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/b67b6886" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b67b6886</a>
• Ensures dynamically generated memory bank IDs preserve raw UTF-8, avoiding incorrect bank selection for non-ASCII identifiers.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/Desko77" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Desko77</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/08a75b5b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>08a75b5b</a>
• Prevents memory compaction from overwriting memories that were meant to be retained.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/9c9a5a29" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>9c9a5a29</a>
• Ensures a session’s final memories are retained on SessionEnd even when retainEveryNTurns is greater than 1.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/starbit-biostar" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@starbit-biostar</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/aefc1ebc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aefc1ebc</a>
• Reads transcript files as UTF-8 to prevent errors or corrupted text when transcripts contain non-ASCII characters.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/tordf" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@tordf</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/eb9be903" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>eb9be903</a>

0.3.1

Bug Fixes

• All Claude Code integration HTTP requests now include an identifying User-Agent for better compatibility and observability. (`9372462e`)

0.3.0

Features

• Claude Code integration now retains tool calls as structured JSON for more accurate memory and retrieval. (`8cb8b912`)

0.2.0

Features

• Added a Claude Code integration plugin for capturing and using Hindsight memory in Claude Code. (`f4390bdc`)
• Claude Code integration can retain full sessions with document upsert and configurable tagging. (`2d31b67d`)

Improvements

• Improved Claude Code plugin installation and configuration experience. (`35b2cbb6`)
• Integrations no longer rely on hardcoded default models, allowing model selection to be fully configured. (`58e68f3e`)
• Claude Code now starts the Hindsight background daemon automatically at session start for smoother operation. (`26944e25`)

Bug Fixes

• Added a supported setup command to register hooks reliably, fixing hook registration issues. (`22ca6a8d`)
• Fixed Claude Code integration compatibility on Windows. (`a94a90ea`)

import PageHero from '@site/src/components/PageHero';

<PageHero title="Cline Changelog" subtitle="Hindsight memory integration for the Cline coding agent." />

← Cline integration

0.2.0

Features

• Added a pip-installable "hindsight-cline" package with a CLI to install and run the Hindsight Cline integration.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/36e31c675" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>36e31c675</a>

0.1.0

Features

• Added Cline integration that captures task lifecycle and prompt events and stores them in Hindsight memory via installable hooks.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/66e58a23" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>66e58a23</a>

cloudflare-oauth-proxy Integration Changelog

Changelog for `hindsight-cloudflare-oauth-proxy`.

For the source code, see `hindsight-integrations/cloudflare-oauth-proxy`.

← Back to main changelog

1.0.1

Features

• Added support for using a Cloudflare OAuth proxy with self-hosted Hindsight for authentication. (`aad07a14`)

import PageHero from '@site/src/components/PageHero';

<PageHero title="OpenAI Codex CLI Changelog" subtitle="Hindsight memory integration for OpenAI Codex CLI." />

← Codex CLI integration

0.3.0

Improvements

• Added a configurable timeout for Codex recall to prevent long-running recalls from hanging.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/voarsh2" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@voarsh2</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/eb76510a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>eb76510a</a>

Bug Fixes

• Filtered out synthetic AGENTS startup messages so they don’t pollute saved memories or transcripts.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/voarsh2" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@voarsh2</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/b41e5e36" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b41e5e36</a>
• Fixed PowerShell-related encoding issues when running the Codex integration on Windows.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/jerviscui" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@jerviscui</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/b837e66c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b837e66c</a>
• Improved UTF-8 handling when reading transcripts and deriving bank IDs, preventing corrupted non-ASCII memory identifiers/content.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/Desko77" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Desko77</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/08a75b5b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>08a75b5b</a>

0.2.1

Improvements

• All Codex integration HTTP requests now include an identifying User-Agent header for better request tracking and compatibility. (`9372462e`)

0.2.0

Features

• Retain structured Codex tool calls from rollout files so they’re preserved in Hindsight memory. (`3461398b`)

0.1.1

Features

• Added Hindsight memory integration for the OpenAI Codex CLI, enabling Codex to use and store memories in Hindsight. (`0b17a67c`)

0.1.0

Features

• Added Hindsight memory integration for OpenAI Codex CLI with three hook scripts: SessionStart (daemon warm-up), UserPromptSubmit (auto-recall), and Stop (auto-retain). (`0b17a67c`)
• Full-session retain with session-level upsert using session ID as document ID. (`0b17a67c`)
• Dynamic bank IDs for per-project memory isolation. (`0b17a67c`)
• Automatic daemon lifecycle management with background pre-start. (`0b17a67c`)
• 57 automated tests covering content processing and end-to-end hook behavior. (`71125cd9`)

Composio Integration Changelog

Changelog for `hindsight-composio`.

For the source code, see `hindsight-integrations/composio`.

← Back to main changelog

0.1.0

Features

• Added Composio integration to expose Hindsight memory as custom tools for Composio-enabled workflows.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/1c9ba0e65" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1c9ba0e65</a>

Continue Integration Changelog

Changelog for `hindsight-continue`.

For the source code, see `hindsight-integrations/continue`.

← Back to main changelog

0.1.0

Features

• Added Continue.dev integration via an HTTP context provider.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c05ab910" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c05ab910</a>

import PageHero from '@site/src/components/PageHero';

<PageHero title="CrewAI Changelog" subtitle="hindsight-crewai — persistent memory for CrewAI agents." />

← CrewAI integration

0.4.20

Features

• Added CrewAI integration enabling persistent memory for crews via Hindsight. (`41db2960`)

Improvements

• All HTTP requests now include an identifying User-Agent header for better compatibility and observability with upstream services. (`9372462e`)
• Improved type-checking support for Python users by shipping PEP 561 type information in all packages. (`d054b884`)
• Security updates applied to address known dependency vulnerabilities. (`300d089b`)

Cursor CLI Integration Changelog

Changelog for `hindsight-cursor-cli`.

For the source code, see `hindsight-integrations/cursor-cli`.

← Back to main changelog

0.2.0

Features

• Cursor CLI integration is now available as a pip-installable package (hindsight-cursor-cli) with a Python-based installer/CLI for setup and hook installation.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c6dd08944" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c6dd08944</a>

0.1.0

Features

• Added a Cursor CLI integration for Hindsight, including install/uninstall scripts, session hooks, and commands to retain and recall memories during Cursor sessions.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/Korayem" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@Korayem</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/dbfe83a2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dbfe83a2</a>

import PageHero from '@site/src/components/PageHero';

<PageHero title="Cursor Changelog" subtitle="hindsight-memory - Hindsight memory plugin for Cursor." />

← Cursor integration

0.2.0

Features

• Added a Hindsight memory plugin integration for Cursor.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/91d767cdc" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>91d767cdc</a>

0.1.0

Features

• Added a Hindsight memory plugin for Cursor using Cursor's plugin hooks for automatic recall and retain.
• Added Cursor-native extras including an always-on rule and an on-demand hindsight-recall skill.
• Added support for local daemon mode, external Hindsight APIs, and native MCP as an alternative integration path.
• Added automated tests covering config loading, bank derivation, content formatting, and hook behavior.

Dify Integration Changelog

Changelog for `hindsight-dify`.

For the source code, see `hindsight-integrations/dify`.

0.1.1

Features

• Added Dify integration, enabling Hindsight memory tools to be used within Dify workflows.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/bc23750b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>bc23750b</a>

Flowise Integration Changelog

Changelog for `@vectorize-io/flowise-nodes-hindsight`.

For the source code, see `hindsight-integrations/flowise`.

← Back to main changelog

0.1.0

Features

• Added Flowise integration for Hindsight, enabling use of Hindsight memory tools within Flowise workflows.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/41ad2b55" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>41ad2b55</a>

Google ADK Integration Changelog

Changelog for `hindsight-google-adk`.

For the source code, see `hindsight-integrations/google-adk`.

← Back to main changelog

0.1.0

Features

• Added Google ADK integration for Hindsight, enabling Hindsight to work with Google ADK-based agents.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c032a74f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c032a74f</a>

Haystack Integration Changelog

Changelog for `hindsight-haystack`.

For the source code, see `hindsight-integrations/haystack`.

← Back to main changelog

0.1.1

This release contains internal maintenance and infrastructure changes only.

0.1.0

Features

• Added a Haystack integration for Hindsight, enabling use of Hindsight memory tools within Haystack pipelines.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/394d66e6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>394d66e6</a>

import PageHero from '@site/src/components/PageHero';

<PageHero title="LangGraph Changelog" subtitle="hindsight-langgraph — LangGraph and LangChain memory integration." />

← LangGraph integration

0.2.0

Breaking Changes

• Updated the LangGraph integration API by removing the legacy BaseStore-based store and adjusting nodes/tools to use the new memory instructions flow.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/b67e813a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b67e813a</a>

Improvements

• Improved LangGraph integration reliability by fixing graph nodes and adding expanded end-to-end and flow tests.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/b67e813a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b67e813a</a>

0.1.2

Improvements

• Improved Python typing support for the Hindsight LangGraph integration (added PEP 561 py.typed marker) so type checkers work correctly. (`d054b884`)
• Updated dependencies to address critical/high security vulnerabilities in the Hindsight LangGraph integration. (`ee4510a7`)

Bug Fixes

• All HTTP requests from the Hindsight LangGraph integration now include a consistent identifying User-Agent header. (`9372462e`)

0.1.1

Features

• Added LangGraph integration for Hindsight. (`b4320254`)

import PageHero from '@site/src/components/PageHero';

<PageHero title="LiteLLM Changelog" subtitle="hindsight-litellm — universal LLM memory integration via LiteLLM." />

← LiteLLM integration

0.5.4

Bug Fixes

• Fixes LiteLLM integration reliability by correcting injection mode behavior, ensuring context-manager state is restored properly, and making validation/errors consistent.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/dfe74b1d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dfe74b1d</a>

0.5.3

This release contains internal maintenance and infrastructure changes only.

0.5.2

Bug Fixes

• Fix conversation storage when using streaming LiteLLM responses.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/ac5181f5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ac5181f5</a>

0.5.1

Improvements

• Add bundled type information for better type-checking support when using the integration in typed Python projects. (`d054b884`)
• Improve security and stability by updating and constraining the LiteLLM dependency, including excluding a compromised version. (`8a2388a4`)

Bug Fixes

• Set an identifying User-Agent header on all HTTP requests to improve compatibility with providers and proxies. (`9372462e`)

0.5.0

Features

• Add streaming support when using the LiteLLM wrapper integration. (`665877bb`)
• Add async retain and reflect support, along with a cleaned-up LiteLLM integration API. (`1d4879a2`)
• Initial release of the Hindsight LiteLLM integration implementation. (`dfccbf29`)

Improvements

• Support sending tags and mission metadata through the LiteLLM integration to improve memory organization and retrieval. (`f3c5a9c1`)

Bug Fixes

• When no explicit Hindsight query is provided, the integration now uses the most recent user message as the query to avoid missing/empty memory lookups. (`5e8952c5`)
• Fix API key handling by passing the configured api_key through to the Hindsight client in the LiteLLM integration. (`c0ca9b02`)

LlamaIndex Integration Changelog

Changelog for `hindsight-llamaindex`.

For the source code, see `hindsight-integrations/llamaindex`.

← Back to main changelog

0.1.5

Improvements

• Replaced the deprecated manual test with a gated end-to-end test suite, improving integration reliability without requiring a real LLM for every run.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/ed34756c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ed34756c</a>

Bug Fixes

• LlamaIndex integration now defaults to using Hindsight Cloud, improving out-of-the-box connectivity and reducing setup issues.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/ed34756c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ed34756c</a>

0.1.4

Improvements

• All HTTP requests now include a consistent identifying User-Agent header. (`9372462e`)
• Improved Python type-checking support by shipping a PEP 561 marker file in the package. (`d054b884`)
• Updated dependencies to address critical and high-severity security vulnerabilities. (`ee4510a7`)

0.1.3

Bug Fixes

• Fixed LlamaIndex integration issues with document IDs, the memory API, and ReAct trace handling to improve reliability and correctness. (`d93dfea8`)

0.1.2

Features

• Added LlamaIndex integration for Hindsight. (`2d787c4f`)

n8n Integration Changelog

Changelog for `@vectorize-io/n8n-nodes-hindsight`.

For the source code, see `hindsight-integrations/n8n`.

0.1.3

Improvements

• Improved reliability and compatibility of the Hindsight n8n node by removing the runtime dependency on the Hindsight client and making direct HTTP requests instead.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/e18ab10a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>e18ab10a</a>

0.1.2

Bug Fixes

• Synced the n8n Hindsight integration with recent configuration changes to keep documentation and node behavior consistent.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/23dc07b0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>23dc07b0</a>

0.1.1

Features

• Added an n8n community node package to integrate Hindsight Memory into n8n workflows.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c1eaf711" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c1eaf711</a>

Bug Fixes

• Fixed the n8n Hindsight node packaging/authentication so it loads correctly and sends the proper authorization header.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/ad4c0e77" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ad4c0e77</a>

import PageHero from '@site/src/components/PageHero';

<PageHero title="NemoClaw Changelog" subtitle="@vectorize-io/hindsight-nemoclaw — persistent memory for NemoClaw sandboxed agents." />

← NemoClaw integration

0.1.2

This release contains internal maintenance and infrastructure changes only.

0.1.1

Features

• Added a setup CLI package for the Hindsight nemoclaw integration. (`d284de28`)

Obsidian Integration Changelog

Changelog for `@vectorize-io/hindsight-obsidian`.

For the source code, see `hindsight-integrations/obsidian`.

← Back to main changelog

0.1.2

Bug Fixes

• Fixes an issue in the Obsidian chat view to meet community-store review requirements for v0.1.2.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c06e85b64" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c06e85b64</a>

0.1.1

Features

• Improved chat note viewing with grounded-note citations, collapsed-by-default behavior, persisted layout, and inline depth controls.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/fe404efb2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>fe404efb2</a>

0.1.0

Features

• Introduces the Hindsight Obsidian plugin, enabling in-editor Hindsight chat and syncing Obsidian notes/memory with Hindsight.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/b0f86f9c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b0f86f9c</a>

OMO Integration Changelog

Changelog for `hindsight-omo`.

For the source code, see `hindsight-integrations/omo`.

← Back to main changelog

0.1.0

Features

• Added a new Oh-My-OpenAgent (OMO) integration for Hindsight, including hooks and scripts to retain and recall memories across sessions.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/dcbouius" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dcbouius</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/6dc56498" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>6dc56498</a>

openai-agents Integration Changelog

Changelog for `hindsight-openai-agents`.

For the source code, see `hindsight-integrations/openai-agents`.

← Back to main changelog

0.1.2

Improvements

• Improved OpenAI Agents integration reliability by defaulting to the Cloud backend and adding gated end-to-end tests with real-LLM bucketing.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c01fc12f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c01fc12f</a>

0.1.1

Improvements

• Documentation and test polish: corrected the openai-agents SDK version requirement, added memory_instructions() to the README and API reference, added a Production Patterns section to the README (error handling, bank lifecycle, multi-agent workflows), and added a dedicated test_config.py covering defaults, configure, env var fallback, and reset.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/52c148c2" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>52c148c2</a>

0.1.0

Features

• Added integration with the OpenAI Agents SDK for Hindsight’s AI memory workflows.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/b8da88c8" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>b8da88c8</a>

import PageHero from '@site/src/components/PageHero';

<PageHero title="OpenClaw Changelog" subtitle="@vectorize-io/hindsight-openclaw — Hindsight memory plugin for OpenClaw." />

← OpenClaw integration

0.8.0

Improvements

• Openclaw now defaults recall types to include only observations, reducing unexpected memory recall behavior out of the box.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/4b19a0fb" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4b19a0fb</a>
• Injected memory context now labels the “Current time” value as UTC for clearer, consistent time interpretation.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/dc41f6a5" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>dc41f6a5</a>

Bug Fixes

• Ensures any un-retained conversation turns are flushed and saved when a session ends, preventing missing memories.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/7a4400e0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7a4400e0</a>
• Fixes dispatch being silently skipped in synthetic-main + static-banking configurations, restoring expected memory processing.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/09c9cecf" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>09c9cecf</a>

0.7.7

Features

• Retained transcripts now include a session-context block at the beginning to preserve important session details.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/kryptt" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@kryptt</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/be696b0d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>be696b0d</a>

Bug Fixes

• Setup wizard now correctly backfills the plugin allowlist to include hindsight-openclaw, preventing the integration from being unintentionally blocked after setup.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/4088af36" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>4088af36</a>

0.7.6

Bug Fixes

• Setup wizard now preserves your existing OpenClaw token and URL when re-running setup, preventing unnecessary reconfiguration.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/ef600683" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>ef600683</a>

0.7.5

Bug Fixes

• Setup wizard now correctly saves the “Allow conversation access” setting for OpenClaw.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/abf84872" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>abf84872</a>

0.7.4

Bug Fixes

• Fixes OpenClaw integration configuration so the knowledge tools toggle is correctly honored.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c95206e0" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c95206e0</a>

0.7.3

Improvements

• Added optional performance timing debug output for the OpenClaw integration.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/d37940a9" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>d37940a9</a>

Bug Fixes

• Fixed mission handling semantics and corrected the allowed configuration options (including retainQueue).<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/aca03832" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>aca03832</a>
• Prevented duplicate OpenClaw registration across multiple API instances to avoid repeated handlers or side effects.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vernmic" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@vernmic</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/0ce9f333" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>0ce9f333</a>

0.7.2

This release contains internal maintenance and infrastructure changes only.

0.7.1

Bug Fixes

• Fix OpenClaw integration upgrades by using the published agent-sdk dependency and updating the plugin configuration schema.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c1924e9d" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c1924e9d</a>

0.7.0

Features

• Added initial support for self-driving agents in the OpenClaw integration for Hindsight.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/7f30dcc7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7f30dcc7</a>

0.6.6

Bug Fixes

• Retention is now applied correctly for default agent main:main sessions instead of being silently skipped.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/70677457" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>70677457</a>

0.6.5

Bug Fixes

• Fix per-session memory retention so saving a new turn no longer overwrites earlier turns in the same session.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/nicoloboschi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@nicoloboschi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/1f897314" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>1f897314</a>
• Improve direct-execution detection by correctly resolving full symlink chains, preventing incorrect behavior when invoked through symlinked paths.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/D2758695161" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@D2758695161</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/7ceaa22a" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>7ceaa22a</a>

0.6.4

Features

• Openclaw now uses a session-scoped document ID and records structured timestamps for each message, improving session consistency and message ordering. (`33645e08`)

0.6.3

Features

• Inline retain tags are now merged with default retain tags, improving consistency of retention behavior without extra configuration. (`b79ab2b7`)

Improvements

• All HTTP requests now include an identifying User-Agent, improving request attribution and compatibility with stricter endpoints. (`9372462e`)

Bug Fixes

• Per-agent banking now respects identity skip-filter configuration, preventing incorrect identity filtering. (`90a22016`)

0.6.2

Features

• OpenClaw conversations are now stored in an Anthropic-style JSON format, preserving tool_use/tool_result blocks for more faithful replay and analysis. (`adc85129`)

Bug Fixes

• Improved session consistency and reduced noise by stabilizing session identity and skipping non-user operational turns. (`2ff805d6`)
• Fixed intermittent missing behavior by ensuring agent hooks are registered on every plugin invocation. (`1be5ff33`)

0.6.1

Bug Fixes

• Openclaw setup wizard now prompts for the actual token value instead of an environment variable name. (`9679d813`)

0.6.0

Breaking Changes

• Configuration is now read from the plugin configuration instead of environment variables, requiring updates to existing deployments. (`e22ae05f`)

Features

• Adds an interactive setup wizard with Cloud, API, and Embedded configuration modes. (`87322396`)
• Adds a daemon lifecycle package for running the Hindsight "all" daemon. (`576016f5`)
• Adds a configuration-aware CLI to backfill historical data into Hindsight memory. (`72fd3d59`)
• Adds session pattern filtering to ignore or treat certain sessions as stateless. (`5a61ac50`)
• Adds configurable tags for retained memories. (`b0e8ac0f`)
• Adds support for bankId when using static banks. (`0e81d1a2`)

Improvements

• Improves startup resilience and enriches retained memory metadata. (`1f1716bd`)
• Adds a JSONL-backed retain queue to improve reliability when the external API is unavailable. (`087545cc`)
• Reduces CLI startup time by deferring heavy initialization until the service starts. (`41025c3b`)

Bug Fixes

• Avoids misrouting by ignoring ctx.channelId when it contains a provider name. (`d4b8b354`)

0.5.1

Bug Fixes

• Fixed JSON manifest formatting issues in the OpenClaw plugin to prevent manifest parsing/loading problems. (`704e41fa`)

0.5.0

Breaking Changes

• Removed hardcoded default model settings from integrations so model/provider must be configured explicitly. (`58e68f3e`)

Features

• Added configurable, structured logging for the OpenClaw integration. (`d441ab81`)
• Added an auto-recall toggle and support for excluding specific providers from recall/retention. (`3f9eb27c`)
• Added configuration to skip recall/retention for selected providers. (`fb7be3ec`)
• Added dynamic per-channel memory banks to isolate memory across channels. (`9a776e9f`)
• Added support for using an external Hindsight API backend. (`6b346925`)
• Added plugin configuration options to select the LLM provider and model. (`8564135b`)

Improvements

• Added control over where recalled memories are injected to better preserve prompt caching. (`200bab23`)
• Improved recall/retention controls and scalability, and added Gemini safety settings support. (`d425e93c`)
• Memory retention now periodically keeps recent conversation turns (default every 10 turns) to improve continuity. (`ad1660b3`)
• Improved OpenClaw and embedding parameters for better integration behavior and configuration. (`749478d9`)
• Improved OpenClaw configuration setup and initialization behavior. (`27498f99`)

Bug Fixes

• Added a configurable auto-recall timeout to prevent recalls from hanging or taking too long. (`cd4d449f`)
• Recalled memories are now injected as system context for more reliable behavior. (`b17f338e`)
• Health check requests now include the auth token to avoid unauthorized failures. (`40b02645`)
• Improved stability and safety with better shell handling, HTTP mode support, lazy reinitialization, and per-user memory banks. (`c4610130`)
• Fixed failures when ingesting very large content (E2BIG). (`6bad6673`)
• Prevented memory retention from recursing indefinitely. (`4f112101`)
• Prevented user memories from being wiped on every new session. (`981cf605`)
• Improved shell argument escaping to prevent command failures with special characters. (`63e2964a`)
• Renamed the OpenClaw binary to the correct name to avoid invocation/config mismatches. (`b364bc34`)

OpenHands Integration Changelog

Changelog for `hindsight-openhands`.

For the source code, see `hindsight-integrations/openhands`.

← Back to main changelog

0.1.0

Features

• Added OpenHands integration with native MCP configuration and memory recall/retain behavior rules.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/DK09876" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@DK09876</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/65862c4f" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>65862c4f</a>

Paperclip Integration Changelog

Changelog for `@vectorize-io/hindsight-paperclip`.

For the source code, see `hindsight-integrations/paperclip`.

← Back to main changelog

0.2.3

Features

• Added per-user memory isolation for Paperclip by supporting configurable bank granularity.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/beca4b42" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>beca4b42</a>

0.2.2

Improvements

• Updated dependencies to address known security vulnerabilities (npm and pip).<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/dcbouius" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@dcbouius</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/26c5028c" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>26c5028c</a>

Bug Fixes

• Fixed the Paperclip integration to correctly handle real Paperclip event payloads, improving reliability of event processing.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/amirhmoradi" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@amirhmoradi</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/be908d5b" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>be908d5b</a>

0.2.1

Breaking Changes

• Replaced the Paperclip integration with the new Paperclip plugin (v0.2.0), changing how the integration is packaged and used.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/c571fac7" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>c571fac7</a>

0.2.0

Breaking Changes

• Rewritten as a proper Paperclip plugin (installed via pnpm paperclipai plugin install). No code changes required — memory hooks run automatically via the event system.
• Works with all adapter types (Claude, Codex, Cursor, HTTP, Process). Previously required manual recall()/retain() calls and only supported HTTP adapter agents.

Features

• agent.run.started hook: auto-recalls context keyed to issue title + description
• agent.run.finished hook: auto-retains agent output with runId as document ID
• hindsight_recall and hindsight_retain agent tools for mid-run memory access
• onValidateConfig: live connectivity check when operator saves settings
• Configurable bank granularity (company+agent, company-only, agent-only)

0.1.2

Improvements

• Paperclip integration now sends an identifying User-Agent on all HTTP requests for better request tracing and compatibility. (`9372462e`)

0.1.1

Features

• Added the Hindsight Paperclip TypeScript integration. (`81441ee9`)

Bug Fixes

• Fixed issues in the Paperclip integration based on review feedback. (`7863ffeb`)

Pipecat Integration Changelog

Changelog for `hindsight-pipecat`.

For the source code, see `hindsight-integrations/pipecat`.

← Back to main changelog

0.1.1

Features

• Added Pipecat voice AI pipeline integration to store and use memories in Hindsight.<span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/benfrank241" target="_blank" rel="noopener noreferrer" style={{color: "var(--ifm-color-primary)", textDecoration: "none", display: "inline-flex", alignItems: "center", gap: "4px", verticalAlign: "middle"}}>@benfrank241</a><span style={{color: "var(--ifm-color-emphasis-500)", margin: "0 0.3em"}}>·</span><a href="https://github.com/vectorize-io/hindsight/commit/f7cc9ad6" target="_blank" rel="noopener noreferrer" style={{fontFamily: "var(--ifm-font-family-monospace, monospace)", fontSize: "0.85em", color: "var(--ifm-color-emphasis-600)"}}>f7cc9ad6</a>

import PageHero from '@site/src/components/PageHero';

<PageHero title="Pydantic AI Changelog" subtitle="hindsight-pydantic-ai — persistent memory tools for Pydantic AI agents." />

← Pydantic AI integration

0.4.20

Features

• Added Pydantic AI integration to provide persistent agent memory in Hindsight. (`cab5a40f`)

Improvements

• Set an identifying User-Agent header on all HTTP requests made by clients. (`9372462e`)
• Added a PEP 561 py.typed marker so type checkers recognize bundled type hints. (`d054b884`)
• Updated dependencies to address critical and high-severity security vulnerabilities. (`ee4510a7`)