agent-memory MCP Server
tigerless-labs/agent-memory
[](https://agentrank-ai.com/tool/tigerless-labs--agent-memory/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
tigerless-labs/agent-memory is a Python tool licensed under MIT. Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key. Topics: agent-memory, ai-agents, claude-code, codex, llm, local-first, long-term-memory, markdown, mcp, python, retrieval, sqlite.
Ranked #4696 out of 24846 indexed tools.
Has 3,404 GitHub stars.
Ecosystem
Score Breakdown
3,404 stars → well-known project
Last commit 1mo ago → recently updated
2/57 issues closed → many open issues
8 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/tigerless-labs--agent-memory/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/tigerless-labs--agent-memory/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/tigerless-labs--agent-memory" alt="AgentRank"></a> Matched Queries
From the README
<div align="center"> ### agent-memory: the long-term memory runtime for AI agents <a href="CLAUDE.md">Invariants</a> · <a href="skills/agent-memory/SKILL.md">Skill</a> · <a href="https://github.com/tigerless-labs/agent-memory/issues">Issues</a> </div> *** An agent that closes its session forgets everything it learned in it. agent-memory is the runtime that fixes that, for any agent — not only coding ones. Markdown files in one store are the single source of truth, the SQLite index beside them is a cache you can delete at any time, and Claude Code, Codex CLI, and anything else that can run a shell command share that store. Retrieval is local and ranked, and it answers with paths rather than pasted text — the agent opens each hit only as deep as the task needs. Writes do not wait for the agent to remember to make them: they fire at conversation boundaries. A sleep-time pass then consolidates and forgets by value, on its own clock. None of it needs an API key. ## Two lines, one stoRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.