ourmem

ourmem / omem

Public

Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code, OpenClaw, MCP Server.

ourmem.ai ai-agent ai-memory claude-code lancedb llm
12
2
100% credibility
Found Mar 30, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

OMEM is a persistent shared memory system for AI agents that enables recall across sessions, devices, and teams via plugins for coding tools and self-hostable servers.

How It Works

1
📰 Discover ourmem

You hear about ourmem, the tool that gives your AI assistants lasting memory so they remember preferences and decisions across chats.

2
Pick your path
🛠️
Use with AI tools

Tell your AI coder to install the ourmem add-on with one simple message.

🏠
Run your own

Start a personal memory service on your computer in moments.

3
🔗 Connect everything

Link your AI assistant to ourmem so it can save and recall important info automatically.

4
💡 Magic happens

In your next chat, your AI pulls up past context instantly, feeling smarter and more personal.

5
👥 Share with others

Create team spaces to let everyone’s AI agents share knowledge without starting over.

🎉 Smarter together

Your AI team now builds on shared wisdom, saving time and avoiding repeat work forever.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 12 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 omem?

OMEM provides persistent, shared memory for AI agents, fixing amnesia where sessions forget preferences, facts, and context. It enables recall across tools like OpenCode, Claude Code, OpenClaw, and MCP servers, plus sharing via personal/team/org spaces—like a shared GitHub repository for agent knowledge. TypeScript plugins hook into agent lifecycles; self-host with Docker for one API key across devices.

Why is it gaining traction?

Stands out with hybrid search (vector + keyword reranking), auto-reconciliation that merges or updates memories, and provenance-tracked sharing, reducing redundant agent work. Devs like the Docker one-liner deploy (~$5/mo object storage) and tools for ingest/search/profile, mirroring shared GitHub actions persisting state over workflows. Plugins auto-capture on session end, no manual saves.

Who should use this?

Multi-agent teams in Claude Code or OpenClaw sharing arch decisions without silos. Custom AI builders needing REST API for memory in products. Solo coders tired of re-teaching agents preferences across machines, like using a shared GitHub project for persistent context.

Verdict

Promising for AI memory woes, with strong docs, benchmarks, and Apache-2.0 openness, but 12 stars and 1.0% credibility signal early maturity—test via eval script first. Prototype if agent silos hurt; hold for prod until more adoption.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.