Skip to main content
Supermemory runs on your own hardware. It’s the same memory engine behind the hosted platform — ingestion, memory extraction, hybrid semantic search, and the full API — as a single self-contained binary.
No Docker. No database to provision. No config files. It boots in seconds with everything built in, and it’s open source.

​
Zero config, actually

Run the binary with nothing set and you get a complete memory system:
  • The Supermemory graph engine, embedded — created automatically on first boot. No database to stand up, no connection strings.
  • Built-in local embeddings — default Xenova/bge-base-en-v1.5 (768d) on your machine, no API key. Same provider stack as cloud if you opt into OpenAI, Gemini, or Ollama — see Embeddings.
  • An API key, generated for you — printed on first boot, ready to paste into any SDK.
  • The full Memory API — /v3/documents, /v4/search, /v4/profile, spaces, the works.
The only thing you bring is a model. In production, Supermemory runs its own proprietary models, purpose-tuned for long-horizon data understanding and memory extraction. Self-hosted, the same pipeline runs on whatever model you point it at — OpenAI, Anthropic, Gemini, Groq, or any OpenAI-compatible endpoint. Bring a key and go. Or don’t bring one at all:

​
Runs fully offline

Supermemory works with any OpenAI-compatible endpoint, which means it runs end-to-end on your machine with a local model — Ollama, LM Studio, vLLM, llama.cpp. gpt-oss-20b is a great fit:
Local graph engine, local embeddings, local LLM. Your data never leaves the building.

​
Drop-in with your existing code

The self-hosted server speaks the same API as the hosted platform. Point any Supermemory SDK at it with a one-line change:
Everything in the Memory API docs works the same way. The coding plugins do too — Claude Code, Codex, and OpenCode all target your local server with SUPERMEMORY_API_URL=http://localhost:6767.

​
Self-hosted vs. the platform

Self-hosted is free, open source, and great for local development, air-gapped environments, and privacy-sensitive workloads. The hosted platform is where the full product lives: If you outgrow a single machine — or want connectors, MCP, and the best-tuned extraction pipeline — the platform is one baseURL change away. Running this for a team or organization? See Local vs. Enterprise.

​
Next steps

Quickstart

Install, run, and store your first memory in under two minutes

Configuration

Every environment variable: LLM providers, storage, auth, tuning

Embeddings

Local default, remote providers, multilingual, dimension lock