#19 · Primary category: AI Data Infrastructure & Storage

LongMemory

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:08/30/26

GitHub Stars

4.5K

Forks

503

Contributors

50

License

Apache-2.0

Why we included this project

LongMemory is for teams whose agents or chat apps keep forgetting what happened in earlier sessions. Instead of treating memory as a vector index, it stores long-term context in a self-hosted SQLite or Postgres backend, with Python and Node SDKs and integrations for LangChain, CrewAI, AutoGen, Streamlit, and MCP. The model stays stateless while the app remembers user preferences and past events, and explainable traces show why a particular memory was recalled. It can also ingest from GitHub, Notion, Google Drive, and web crawlers, so context can come from where your team already works. One honest caveat: the project is mid-rewrite, so expect breaking changes and rough edges if you adopt it today.

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