Self-hosted AI chat that deploys as one Go binary. Streaming SSE, OpenAI and Anthropic upstreams,...
8.1K
Self-hosted AI chat with OpenAI-compatible and Anthropic models, MCP tools, and an embedded web app. Run one Docker image with SQLite, or use Postgres when needed.
CHATZ_SHOWCASE_MODE=true to return fixed streamed replies for exact demo prompts. Normal chats keep using the selected model.chatz ships as the psyb0t/chatz Docker image. The fastest path uses SQLite in a persistent Docker volume. It needs no LLM configuration for the first run.
docker pull psyb0t/chatz:latest
docker volume create chatz-data
touch chatz.log
sudo chown 1000:1000 chatz.log
docker run --name chatz --detach --restart unless-stopped --init \
--publish 127.0.0.1:8080:8080 \
--env CHATZ_DB_DRIVER=sqlite \
--read-only \
--tmpfs /tmp:rw,noexec,nosuid,size=64m \
--cap-drop ALL \
--security-opt no-new-privileges:true \
--memory 512m \
--cpus 1.0 \
--pids-limit 256 \
--mount type=bind,src="$(pwd)/chatz.log",dst=/app/chatz.log \
--volume chatz-data:/data \
psyb0t/chatz:latest run
Open http://localhost:8080, then visit /setup to create the admin. The chat works before you configure an LLM, but the model picker stays empty.
To connect a model, copy .env.example to .env, keep CHATZ_DB_DRIVER=sqlite, set CHATZ_UPSTREAMS and the key variable it names, and add --env-file .env to the command:
CHATZ_UPSTREAMS=[{"name":"openai","provider":"openai","baseUrl":"https://api.openai.com/v1","apiKeyEnv":"OPENAI_API_KEY"}]
OPENAI_API_KEY=sk-...
The openai provider also covers OpenAI-compatible APIs such as Ollama or AIGate. Set CHATZ_SECRETS_KEY (openssl rand -base64 32) before adding MCP servers with credentials. The getting started guide covers Docker Compose with Postgres and demo mode, and models and upstreams has the full upstream format.
Deploy a v<semver> release tag rather than latest. Pull the image again and recreate the container to upgrade; migrations run on start.
The full documentation lives at psyb0t.github.io/chatz.
| Section | What it covers |
|---|---|
| Getting started | Docker and Docker Compose installs, the first admin, the first model, demo mode |
| Configuration | Every environment variable with its default |
| Models and upstreams | The CHATZ_UPSTREAMS format, model metadata, fallbacks, timeouts and health |
| Chats | Chat settings, the history budget, streaming status, retries and search |
| MCP servers | Adding, importing and toggling MCP servers, and credential encryption |
| Generative UI | The component catalog and how models put UI into a reply |
| HTTP API | Authentication, endpoints, the SSE stream and error codes |
| Deployment | Image tags, SQLite or Postgres, upgrades, backups and TLS |
| Monitoring | Health, admin readiness, Prometheus metrics and logs |
| Security | What chatz protects and what is left to you |
| Troubleshooting | Startup refusals and common errors with their fixes |
| Architecture | How the binary is put together |
| Development | Building, testing and changing chatz from source |
Docker, Make and Bash are enough: every target runs its tools in a development container.
make help # every target
make run # Docker Compose stack from the checkout
make lint # Go, shell and web checks
make test # Go and web unit tests
make test-coverage # integration-tagged Go coverage gate plus web tests
make docs # build the documentation site
The development guide covers the test tiers, code generation and CI. Rules for coding agents and contributors are in AGENTS.md.
MIT, see LICENSE.
Content type
Image
Digest
sha256:33a5a7a4a…
Size
70.5 MB
Last updated
9 days ago
docker pull psyb0t/chatz