Collab2Dev/openclaw-recall

Persistent memory, context compression & profile visibility for 🦞OpenClaw🦞.

38
/ 100
Emerging

Implements four memory types (preference, semantic, episodic, session_state) with hybrid retrieval using RRF-style fusion and retrieval gates to minimize redundant recall. Uses layered context compression with token budgets and tool-output compaction that preserves code blocks and error stacks. Provides diagnostic CLI commands (`doctor`, `status`, `memory explain`, `profile inspect`) and write-time/retrieval-time guardrails to filter noisy or sensitive rows.

No Package No Dependents
Maintenance 13 / 25
Adoption 3 / 25
Maturity 9 / 25
Community 13 / 25

How are scores calculated?

Stars

3

Forks

2

Language

TypeScript

License

Apache-2.0

Category

agent-memory-systems

Last pushed

Mar 21, 2026

Commits (30d)

0

GitHub
Agent Memory Systems · 130 agents

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Collab2Dev/openclaw-recall"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Featured in

Agent Memory in 2026: What Actually Works for Persistent AI Your Agent is Hitting its Ceiling — Who's Actually Fixing It

Higher-rated alternatives

thedotmack/claude-mem

A Claude Code plugin that automatically captures everything Claude does during your coding...

87

Open-Source-Legal/OpenContracts

Humans and AI agents, building knowledge bases together. Self-hosted document annotation,...

71

omega-memory/omega-memory

Persistent memory for AI coding agents

64

volcengine/MineContext

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

60

gengxy1216/FlockMem

✦ FlockMem is a lightweight, local-first long-term collective memory bus for multi-agents,...

56

Explore AI Agents

All categories Trending AI Agent directory Insights