#357 · Primary category: AI Agents & Automation

OpenMemory

ai ai-agents ai-infrastructure ai-memory artificial-intelligence cognitive-architecture embeddings gemini llm long-term-memory memory memory-engine memory-retrieval ollama one-line openai openmemory rag supermemory vector-database

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

Project last updated:08/25/26

GitHub Stars

4.5K

Forks

503

Contributors

50

License

Apache-2.0

Why we included this project

OpenMemory is a self-hosted memory store that gives LLM apps something to hold onto across sessions, so agents stop forgetting what users told them earlier in a conversation. Instead of treating memory as a flat pile of embeddings, it separates facts from preferences and events, weighs how recent and important each entry is, and keeps a temporal graph that lets you ask what was true at a given moment. There are Python and Node SDKs, hooking into LangChain, CrewAI, AutoGen, or OpenAI clients takes a few lines of code, and explainable traces show you why a particular memory got recalled rather than leaving you to trust a black box. Worth knowing before you adopt it: the project is mid-rewrite and the maintainers flag breaking changes.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category