FreeAIRepo
Agents & automation

tigerless-labs/agent-memory

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.

MITPython
Stars
4.4k
Forks
191
Open issues
7
Last push
1d ago

About agent-memory

agent-memory is a free, open-source AI agent tool by tigerless-labs, written mainly in Python. 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. It has 4.4k GitHub stars and 191 forks, and was last updated 1d ago. It's released under the MIT license, a standard open-source license.

License
MIT
Language
Python
Stars
4,429
Last update
1d ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not stated
Self-hostable
Not stated

Similar free tools

All Agents & automation tools →

agent-memory FAQ

Is agent-memory free?

Yes. agent-memory is open source and free to use. It's released under the MIT license, a standard open-source license.

Does agent-memory run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does agent-memory need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is agent-memory still maintained?

Yes. It was last updated 1d ago and has 7 open issues on GitHub.

What are alternatives to agent-memory?

Similar free, open-source tools include hermes-agent, ECC, claude-code-best-practice, ponytail.

Related topics