CaviraOSS/OpenMemory

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

64
/ 100
Established

This project gives AI agents and large language models (LLMs) a persistent, long-term memory. It allows you to feed in information from various sources like GitHub, Notion, or web pages, and the AI can then recall and use these memories contextually over time. It's for developers building AI applications (e.g., chatbots, automated assistants, or intelligent UIs) who want their creations to remember past interactions and information without starting fresh every time.

3,604 stars. Actively maintained with 30 commits in the last 30 days.

Use this if you are a developer building an AI application and need your LLM or agent to have a sophisticated, self-hosted, long-term memory that understands different types of information (facts, events, preferences) and how they change over time.

Not ideal if you only need simple, short-term conversational memory or are looking for a cloud-managed vector database solution without deeper cognitive memory features.

AI agent development LLM application building conversational AI intelligent assistants persistent data for AI
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 21 / 25

How are scores calculated?

Stars

3,604

Forks

412

Language

TypeScript

License

Apache-2.0

Last pushed

Mar 04, 2026

Commits (30d)

30

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/CaviraOSS/OpenMemory"

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