OpenMemory

OpenMemory is a vector database - Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Overview

To contribute, visit https://github.com/CaviraOSS/OpenMemory/tree/rewrite branch. If you find an issue, please open a GitHub issue with details so it can be tracked and resolved.

OpenMemory is a cognitive memory engine for LLMs and agents.

Your model stays stateless. Your app stops being amnesiac.

See the integrations section in the docs for concrete patterns.

• Node backends - CLIs - local tools - anything that needs durable memory without running a separate service.

OpenMemory can run inside your app or as a central service.

LLMs forget everything between messages. Most “memory” solutions are really just RAG pipelines:

It behaves like a memory module, not a “vector DB with marketing copy”.

• Multi-sector memory Episodic (events), semantic (facts), procedural (skills), emotional (feelings), reflective (insights).

• Temporal knowledge graph 'valid_from' / 'valid_to', point‑in‑time truth, evolution over time.

• Composite scoring Salience + recency + coactivation, not just cosine distance.

• Decay engine Adaptive forgetting per sector instead of hard TTLs.

• Explainable recall “Waypoint” traces that show exactly which nodes were used in context.

• Embeddings OpenAI, Gemini, Ollama, AWS, synthetic fallback.

• Integrations LangChain, CrewAI, AutoGen, Streamlit, MCP, VS Code, IDEs.

• Connectors Import from GitHub, Notion, Google Drive, Google Sheets/Slides, OneDrive, Web Crawler.

• Migration tool Import memories from Mem0, Zep, Supermemory and more.

OpenMemory is open-source, written primarily in TypeScript, with 4,206 GitHub stars under the Apache 2.0 license. The latest release is v1.2.3 (2025-12-12).

Key capabilities

From the project's documentation:

• 🧠 Real long-term memory (not just embeddings in a table)
• 💾 Self-hosted, local-first (SQLite / Postgres)
• 🐍 Python + 🟦 Node SDKs
• 🧩 Integrations: LangChain, CrewAI, AutoGen, Streamlit, MCP, VS Code
• 📥 Sources: GitHub, Notion, Google Drive, OneDrive, Web Crawler
• 🔍 Explainable traces (see why something was recalled)

How it fits a local-AI stack

OpenMemory runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related vector databases in the directory:

• Chroma
• Milvus
• Qdrant
• Weaviate

Sources

• Source code & docs: CaviraOSS/OpenMemory
• Official website: https://openmemory.cavira.app

Stats from GitHub, 2026-06-08.