tigerless-labs/agent-memory

2,391 stars · Last commit 2026-10-02

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.

README preview

<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>

![](https://img.shields.io/badge/version-0.1.0-369eff?labelColor=black&style=flat-square)
![](https://img.shields.io/badge/python-3.12+-ffcb47?labelColor=black&style=flat-square)
![](https://img.shields.io/badge/hosts-Claude%20Code%2C%20Codex%20CLI%2C%20Muse%20Code-ff80eb?labelColor=black&style=flat-square)
![](https://img.shields.io/badge/dependencies-zero%20API%20keys-c4f042?labelColor=black&style=flat-square)

</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, Muse Code, and anything else that can run a shell command share
that store.

View full repository on GitHub →