Platform maintainers
The shared engine, extension and API interfaces, tested examples, documentation — and the platform gaps that adoption surfaces.
Build your assistant,
not its infrastructure.
Assistant is a self-hostable engine for assistants that work with your files and tools — not just your questions. Bring profiles, custom tools, skills, and your own domain rules; reuse agent execution, persistence, APIs, and model-provider integrations. Operate the runtime yourself.
Who owns what
The engine is shared. The application is yours.
Application builders
Profiles, custom tools, skills, authored ontology and metrics, source mappings, deterministic domain safeguards, and representative tests.
Deployment teams
Installation, runtime placement, identity and accounts, credentials, permissions, data paths, networking, budgets, observability, backups and recovery.
From source
Five minutes with uv.
Python 3.11+, uv, and one provider key. There is no PyPI package — the assistant installs from source.
Install & run
git clone https://github.com/open-assistants-lab/assistant
cd assistant
uv sync --extra dev # base install; add extras only if needed
cp .env.example .env # add your provider key
echo 'OPENAI_API_KEY=sk-...' >> .env # or ANTHROPIC_API_KEY, or a local Ollama
uv run assistant http # server on 127.0.0.1:8080
curl -s http://localhost:8080/health # -> {"status":"healthy"}User data defaults to ~/Assistant/; the configured data path holds other state — inventory and back up both. Runtime, inference, tools, and tracing are four separate data flows: a local runtime does not mean everything stays local.
Deploy
One container. Your machine. Your data.
The assistant ships as a published Docker image — multi-arch (amd64 + arm64), rebuilt on every release. No clone, no build: pull, compose up, and the server answers on 127.0.0.1:8080.
Pull & run
docker pull ghcr.io/open-assistants-lab/assistant:latest
mkdir -p assistant-deploy && cd assistant-deploy
curl -sO https://raw.githubusercontent.com/open-assistants-lab/assistant/main/docker/docker-compose.yaml
curl -sO https://raw.githubusercontent.com/open-assistants-lab/assistant/main/docker/.env.example
cp .env.example .env # add your LLM provider key
# swap the build: block for the published image, then:
docker compose up -d
curl -s http://localhost:8080/health # -> {"status":"healthy"}Published image
ghcr.io/open-assistants-lab/assistant:latest — multi-arch, rebuilt on every release tag and main push. Full feature set: semantic memory, analytics, tool index.
Loopback only
Binds 127.0.0.1:8080 with a built-in healthcheck — the server never exposes itself to the network.
Your data, mounted
./data:/app/data persists per-user stores; config.yaml is mounted so admin edits apply with a restart — no rebuild.
Enterprise mode
Container-per-tenant-user deployment with per-user API keys — generated by scripts/generate_enterprise_compose.sh.