agent-memory
agent-memory is a long-term memory runtime that lets AI agents like Claude Code and Codex remember past sessions, using plain Markdown files, with no API key.
What it is good for
- Keeping what an agent learned after a session closes
- Sharing one memory store across several coding agents
- Finding past decisions and notes without pasting old text
- Keeping memory files readable and portable outside the tool
At a glance
- Who it is for
- Setup
- Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- Agent app
- Tasks
- Works with
- Claude Code, Codex CLI, Muse Code, Hermes, Claude Desktop, ChatGPT
Momentum
- Rank this week
- Not ranked (last #91, week 41, 2026)
- Best rank
- #33 week 40, 2026
- GitHub stars
- 4,307
GitHub numbers as of Nov 2, 2026. Updated weekly.
Ranking history
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is agent-memory free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use agent-memory?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does agent-memory work with?
- According to its own documentation, it works with Claude Code, Codex CLI, Muse Code, Hermes, Claude Desktop, and ChatGPT.
- What is agent-memory good for?
- Keeping what an agent learned after a session closes, sharing one memory store across several coding agents, finding past decisions and notes without pasting old text, and keeping memory files readable and portable outside the tool.
Similar agents
- OmO
OmO is a coding agent app that turns a single prompt into finished software work for developers and builders who want agents to handle multi-step jobs.
- LoopX
LoopX is a local-first control plane that keeps long-running agent work on goals, decisions and evidence across sessions and tools for engineers and researchers.
- Synthadoc
Synthadoc is an open-source tool that turns raw documents into a structured, local Markdown wiki that stays accurate as sources grow, for individuals and teams.
- Product-Manager-Skills
Product-Manager-Skills is a library of 77 product management frameworks that teaches Claude, Codex, and similar agents to write PRDs, plan discovery, and set priorities for product managers.
- SoloMD
SoloMD is a markdown note editor that lets AI agents like Claude Code and Cursor read and edit your notes folder for people who keep their notes as files.
- Orca
Orca is a desktop app that runs and tracks several coding agents at once, each in its own worktree, for developers and vibe coders.