Reasoningbank With Agentdb
- 986 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
reasoningbank-with-agentdb is a Claude Code skill that gives agents adaptive learning, experience replay, memory distillation, and continuous decision improvement using AgentDB vector storage for developers who need pers
About
reasoningbank-with-agentdb is a Claude Code skill from ruvnet/ruflo that pairs ReasoningBank adaptive learning with AgentDB, a high-performance vector database for agent memory. It supports experience replay, memory distillation, and continuous decision improvement across agent sessions. The skill fits ruflo agent stacks where learning outcomes must persist in vector storage rather than ephemeral context. Developers reach for reasoningbank-with-agentdb when agents need durable experience banks, replay-based strategy refinement, and distilled long-term memory on top of ReasoningBank patterns.
- Implements ReasoningBank adaptive learning with trajectory tracking, verdict judgment, memory distillation and pattern r
- Powered by AgentDB delivering 150x faster pattern retrieval and 500x faster batch operations
- Includes automatic migration from legacy .swarm$memory.db with validation
- Provides 100% backward compatibility while enabling self-learning agent behaviors
- Offers both CLI initialization and TypeScript API integration paths
Reasoningbank With Agentdb by the numbers
- 986 all-time installs (skills.sh)
- +5 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #1,106 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: HIGH risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill reasoningbank-with-agentdbAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 986 |
|---|---|
| repo stars | ★ 67k |
| Security audit | 2 / 3 scanners passed |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do agents persist learning in a vector database?
Give their agents adaptive learning, experience replay, memory distillation, and continuous decision improvement using a high-performance vector database.
Who is it for?
Developers building ruflo agents who need ReasoningBank learning persisted in AgentDB with experience replay and memory distillation.
Skip if: Developers without vector database requirements or agents that only need ephemeral in-context memory without experience replay.
When should I use this skill?
User asks for ReasoningBank with AgentDB, agent experience replay, memory distillation, or vector-backed agent learning.
What you get
AgentDB-backed experience store, replay pipelines, distilled memory indexes, and improved decision policies.
- AgentDB experience store
- replay pipeline
- distilled memory index
Files
Claims Authorization Skill
Purpose
Claims-based authorization for secure agent operations and access control.
Claim Types
| Claim | Description |
|---|---|
read | Read file access |
write | Write file access |
execute | Command execution |
spawn | Agent spawning |
memory | Memory access |
network | Network access |
admin | Administrative operations |
Commands
Check Claim
npx claude-flow claims check --agent agent-123 --claim writeGrant Claim
npx claude-flow claims grant --agent agent-123 --claim write --scope "/src/**"Revoke Claim
npx claude-flow claims revoke --agent agent-123 --claim writeList Claims
npx claude-flow claims list --agent agent-123Scope Patterns
| Pattern | Description |
|---|---|
* | All resources |
/src/** | All files in src |
/config/*.toml | TOML files in config |
memory:patterns | Patterns namespace |
Security Levels
| Level | Claims |
|---|---|
minimal | read only |
standard | read, write, execute |
elevated | + spawn, memory |
admin | all claims |
Best Practices
1. Follow principle of least privilege 2. Scope claims to specific resources 3. Audit claim usage regularly 4. Revoke claims when no longer needed
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
Choose reasoningbank-with-agentdb when agent learning must persist in vector storage; use reasoningbank-intelligence for core adaptive learning integration alone.
FAQ
What does reasoningbank-with-agentdb add over ReasoningBank alone?
reasoningbank-with-agentdb persists ReasoningBank learning in AgentDB vector storage with experience replay and memory distillation. Agents retain and refine strategies across sessions instead of losing outcomes after each run.
When should developers use reasoningbank-with-agentdb?
reasoningbank-with-agentdb fits agent builds needing durable vector-backed memory, replay of past experiences, and distilled long-term knowledge. Use it when decision quality must improve continuously across many agent tasks.
Is Reasoningbank With Agentdb safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.