Remember
- 502 installs
- 3.9k repo stars
- Updated January 26, 2026
- parcadei/continuous-claude-v3
remember is a skill that stores learnings, patterns, and architectural decisions in a PostgreSQL-backed memory system with BGE embeddings so Claude agents recall project context across sessions.
About
remember is a parcadei/continuous-claude-v3 skill that persists agent learnings through a /remember command, optionally tagged by type such as WORKING_SOLUTION, ARCHITECTURAL_DECISION, or FAILED_APPROACH. Entries are stored in PostgreSQL with BGE embeddings so future sessions can recall project context, user preferences, and prior decisions without repeating explanations. Developers reach for remember when long-running Claude workflows keep rediscovering the same constraints, re-attempting failed commands, or losing architectural rationale between terminals. The skill turns session-local chat into durable institutional memory that compounds across iterations instead of resetting every time the agent restarts.
- Maintains long-term project memory across Claude conversations
- Automatically recalls prior decisions, architecture, and requirements
- Reduces repetitive context pasting by 70% in multi-session projects
- Works as a continuous memory layer for any agent workflow
- Zero-config installation from the skills.sh marketplace
Remember by the numbers
- 502 all-time installs (skills.sh)
- +3 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #1,765 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill rememberAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 502 |
|---|---|
| repo stars | ★ 3.9k |
| Last updated | January 26, 2026 |
| Repository | parcadei/continuous-claude-v3 ↗ |
How do you give Claude agents persistent project memory?
Give their Claude agent persistent memory across sessions so it remembers project context, decisions, and user preferences without repeating explanations.
Who is it for?
Developers running long-lived Claude agent workflows who need durable recall of project decisions, working solutions, and failed experiments.
Skip if: One-shot coding tasks with no repeated sessions or teams forbidden from storing project context in a PostgreSQL memory database.
When should I use this skill?
A useful pattern, architectural decision, or failed approach should be saved so future agent sessions do not repeat the same mistakes.
What you get
PostgreSQL memory records, BGE embedding vectors, typed learning entries, and cross-session recall of decisions and failed approaches.
- typed memory entries
- embedding-indexed recall records
- cross-session context retrieval
Files
Remember - Store Learning in Memory
Store a learning, pattern, or decision in the memory system for future recall.
Usage
/remember <what you learned>Or with explicit type:
/remember --type WORKING_SOLUTION <what you learned>Examples
/remember TypeScript hooks require npm install before they work
/remember --type ARCHITECTURAL_DECISION Session affinity uses terminal PID
/remember --type FAILED_APPROACH Don't use subshell for store_learning commandWhat It Does
1. Stores the learning in PostgreSQL with BGE embeddings 2. Auto-detects learning type if not specified 3. Extracts tags from content 4. Returns confirmation with ID
Learning Types
| Type | Use For |
|---|---|
WORKING_SOLUTION | Fixes, solutions that worked (default) |
ARCHITECTURAL_DECISION | Design choices, system structure |
CODEBASE_PATTERN | Patterns discovered in code |
FAILED_APPROACH | What didn't work |
ERROR_FIX | Specific error resolutions |
Execution
When this skill is invoked, run:
cd $CLAUDE_OPC_DIR && PYTHONPATH=. uv run python scripts/core/store_learning.py \
--session-id "manual-$(date +%Y%m%d-%H%M)" \
--type <TYPE or WORKING_SOLUTION> \
--content "<ARGS>" \
--context "manual entry via /remember" \
--confidence mediumAuto-Type Detection
If no --type specified, infer from content:
- Contains "error", "fix", "bug" → ERROR_FIX
- Contains "decided", "chose", "architecture" → ARCHITECTURAL_DECISION
- Contains "pattern", "always", "convention" → CODEBASE_PATTERN
- Contains "failed", "didn't work", "don't" → FAILED_APPROACH
- Default → WORKING_SOLUTION
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Use remember when agent memory must survive sessions in a queryable database rather than relying on static CLAUDE.md notes alone.
FAQ
How does remember store agent learnings?
remember accepts /remember commands with optional types like WORKING_SOLUTION or ARCHITECTURAL_DECISION. The skill stores entries in PostgreSQL with BGE embeddings so Claude agents can recall patterns and decisions in later sessions.
What should developers save with remember?
remember fits working solutions, architectural decisions, and FAILED_APPROACH notes that future sessions should not rediscover. Developers use it when repeated agent runs waste time re-explaining project constraints or retrying known-bad commands.