agentmemory
agentmemory is a persistent memory tool that lets coding agents recall past sessions, decisions and fixes across tools for developers.
What it is good for
- Keeping project history across coding sessions
- Letting one AI coding agent recall fixes from another
- Searching past decisions and lessons from earlier work
- Reviewing and editing what an AI agent has saved
At a glance
- Who it is for
- Setup difficulty
- Technical ยท 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, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, OpenCode
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 30,396
GitHub numbers as of Nov 16, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is agentmemory free?
- Yes. It is free and open source (Apache-2.0 license).
- Do I need to know how to code to use agentmemory?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does agentmemory work with?
- According to its own documentation, it works with Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, and OpenCode.
- What is agentmemory good for?
- Keeping project history across coding sessions, letting one AI coding agent recall fixes from another, searching past decisions and lessons from earlier work, and reviewing and editing what an AI agent has saved.
Similar agents to agentmemory
- Unsloth
Unsloth is a desktop app that runs and trains local AI models, and connects Claude Code and Codex to them, for people who want to run AI on their own computer.
- Skill Seekers
Skill Seekers is a tool that turns documentation sites, GitHub repos, and PDFs into Claude AI skills for developers and AI builders.
- Tutti
Tutti is a shared workspace that lets people and AI agents like Claude Code and Codex pass context, files, and tasks between them without copy-pasting.
- agent-beacon
Beacon is an agent app that captures coding agent session history and turns it into reusable memory for developers using multiple AI coding tools.
- Adelie
Adelie is a local multi-agent app builder that turns a one-sentence description into a runnable agent application for developers and builders.
- Open Walnut
Open Walnut is a self-hosted web app that runs Claude Code sessions on your laptop and remote servers in one place, for developers managing ongoing work.