---
slug: "agent-memory"
name: "agent-memory"
effect: "Gives coding agents a shared long-term memory kept as plain Markdown files, with local ranked recall"
category: "memory"
tier: "rising"
url: "https://github.com/tigerless-labs/agent-memory"
github: "tigerless-labs/agent-memory"
pricing: "open-source"
license: "MIT"
tags: ["memory", "markdown", "claude-code", "codex", "mcp", "cli"]
platforms: ["claude-code", "codex", "any-mcp-client"]
install_kind: "cli"
date_added: "2026-10-15"
rank: 3
rising_score: 70
stars: 3655
star_velocity: 84.4
velocity_basis: "since creation"
created_at: "2026-09-01T21:52:29Z"
pushed_at: "2026-10-14T20:18:38Z"
signals_status: "ok"
signals_fetched_at: "2026-10-15T05:02:32.403Z"
page: "https://agenttooldrop.com/tools/agent-memory"
---

# agent-memory

Gives coding agents a shared long-term memory kept as plain Markdown files, with local ranked recall

Category: Memory. Tier: new and rising, rank 3 by new and rising score (70 of 100). Pricing: Open source. License: MIT.

Platforms: claude-code, codex, any-mcp-client.

## Why you would want it

agent-memory keeps each memory as one Markdown file in a single store, with a SQLite index beside it that can be deleted and rebuilt at any time. Recall runs locally and returns a ranked list of paths with one-line abstracts, so the agent opens only what it needs, and Claude Code, Codex CLI and Muse Code can share the same store. Hooks write memories at conversation boundaries, and a separate sleep-time pass consolidates them, with deletions only arriving as proposals you confirm. It needs no API key of its own and borrows judgement from the host agent's CLI.

## Best for

- Memory shared between Claude Code and Codex
- Memory you can grep and keep in git
- Agents that forget between sessions

## Use it when

You want an agent to remember decisions across sessions and prefer a store you can read, grep and commit over an opaque database.

## Skip it if

You want a packaged install: there is no PyPI release yet, so it installs from a git checkout with uv, and the repo was created on 2026-09-01. Setup writes lifecycle hooks into your agent's settings and runs the host agent's CLI headlessly to distil and consolidate memories.

## Editor note

After installing, `mem setup --host claude-code` or `mem setup --host codex` installs the hooks and skill; add `--mcp` to also register the stdio MCP server.

## Install

Install from a checkout with uv:

```sh
git clone https://github.com/tigerless-labs/agent-memory.git
cd agent-memory
uv sync --all-packages
```

Source: https://github.com/tigerless-labs/agent-memory#install

## Live signals

Fetched 2026-10-15T05:02:32.403Z (status: ok).

- Repository: tigerless-labs/agent-memory
- Repository created: 2026-09-01
- Stars: 3,655 (GitHub's count; it cannot be authenticated)
- Stars per day, since repo creation: 84.4 (an average over the repo's life, not a growth rate)
- Forks: 159
- Open issues and PRs: 56
- License (GitHub): MIT
- Last push: 2026-10-14
- Latest release: none

## Links

- Website: https://github.com/tigerless-labs/agent-memory
- GitHub: https://github.com/tigerless-labs/agent-memory
- Install instructions verified at: https://github.com/tigerless-labs/agent-memory#install
- Source for this entry: https://github.com/tigerless-labs/agent-memory#readme
- AgentToolDrop page: https://agenttooldrop.com/tools/agent-memory
- Full catalog (JSON): https://agenttooldrop.com/tools.json