Local-first AI memory layer. 100% private. Zero cloud. Works with every LLM.
You use ChatGPT, Claude, Cursor, and Gemini every single day. But every new session starts from absolute zero.
This is the AI amnesia problem. MemoryOS fixes it.
1. CAPTURE → Extension watches your AI chats (ChatGPT, Claude, Gemini)
2. STORE → Local SQLite + ChromaDB — 100% on your machine
3. RETRIEVE → Hybrid search: semantic + keyword, injected into any AI chat
# One-line (Linux / macOS)
curl -fsSL https://raw.githubusercontent.com/SamoTech/memoryos/main/scripts/install.sh | bash
# Via pip
pip install memoryos && memoryos start
# Via Docker
git clone https://github.com/SamoTech/memoryos && cd memoryos && docker-compose up -dmemoryos start # Start server + open dashboard
memoryos add "Decided to use Zustand" # Add memory manually
memoryos search "react hooks" # Semantic search
memoryos ask "what auth approach did I use?" # Get AI-ready context
memoryos export --format markdown # Export to MarkdownEdit ~/.memoryos/.env:
EMBEDDING_PROVIDER=local
SUMMARIZER_PROVIDER=ollama
OLLAMA_MODEL=llama3
AUTO_SUMMARIZE=true| Layer | Technology |
|---|---|
| Backend | Python 3.11, FastAPI |
| Database | SQLite + FTS5 |
| Vector DB | ChromaDB |
| Embeddings | sentence-transformers |
| Summarization | Ollama / Groq / OpenAI |
| Dashboard | Next.js 14 + TypeScript |
| Extension | Chrome MV3 |
MIT — see LICENSE for details.
Built with ❤️ by SamoTech · Local-first AI memory