aayoawoyemi/Ori-Mnemos

Local-first persistent memory for AI agents. Knowledge graph + ACT-R decay + three-signal retrieval. Agents wake up as themselves. MCP server (14 tools) for Claude, Cursor, Windsurf, Cline.

31
/ 100
Emerging

Ori Mnemos provides AI agents with a long-term memory system, allowing them to retain identity, knowledge, and operational details across sessions and different tools. It takes in plain text notes and wiki-links, and outputs relevant, context-aware information, enabling AI agents to 'wake up as themselves' and learn over time. This is for developers building and managing sophisticated AI agents that need to remember past interactions and information.

Use this if you are developing AI agents that require robust, persistent memory, and you want to ensure they maintain their identity and knowledge without relying on external cloud services or complex database setups.

Not ideal if your AI agent only needs short-term memory or if you prefer a fully managed, cloud-based memory solution with minimal local setup.

AI-agent-development persistent-memory knowledge-management conversational-AI local-first-AI
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 3 / 25

How are scores calculated?

Stars

34

Forks

1

Language

TypeScript

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/aayoawoyemi/Ori-Mnemos"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.