mem9-ai

mem9-ai / mem9

Public

Unlimited memory for OpenClaw

362
44
100% credibility
Found Mar 16, 2026 at 362 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

mem9 is a persistent shared memory system for AI coding agents that prevents forgetting across sessions and enables multi-agent collaboration.

How It Works

1
💭 Notice your AI helper forgets

You chat with your coding assistant, but it forgets key details like project names or preferences after each session.

2
🪶 Discover mem9 memory jar

You find mem9, a simple way to give your AI a persistent memory that sticks between chats and devices.

3
🔗 Get your shared memory space

Sign up for free and create a private memory space for your team or solo projects.

4
🤖 Connect your AI helpers

Link your favorite coding AIs like Claude or others so they all share the same memory pool.

5
💾 Chat and memories save automatically

As you work, important facts and notes are quietly saved to your memory jar without extra effort.

🧠 Switch anytime, nothing lost

Jump between devices or AIs—your project details, preferences, and plans are always there, shared and up to date.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 362 to 362 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is mem9?

mem9 delivers persistent, shared memory for AI agents like Claude Code, OpenClaw, and OpenCode, ending the amnesia where agents forget sessions and can't collaborate across tools or devices. Run a Go server on TiDB Cloud's free tier for hybrid vector/keyword search over unlimited memories, with TypeScript plugins that auto-load/save via lifecycle hooks. Get REST API access for custom clients, turning siloed local files into team-wide unlimited memory ai chat.

Why is it gaining traction?

362 stars reflect the hook: stateless plugins share one memory pool via simple curl provisioning, no OpenAI keys for embeddings, and MySQL-compatible migration path. Beats file-based amnesia with multi-agent recall – store via CLI or skills, search semantically/keyword-style. Free TiDB tier handles most solo/team loads without ops hassle.

Who should use this?

Devs wielding Claude Code or OpenClaw for ongoing projects, tired of re-teaching agents context after restarts. Teams blending agents like OpenCode + custom HTTP clients for shared discoveries. Solo coders jumping machines, needing memories that stick without manual exports.

Verdict

Try it for agent persistence today – quick plugins and API shine – but 1.0% credibility score signals early days: sparse tests, dashboard incoming. Pairs well with unlimited github copilot vscode flows; monitor for production hardening.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.