gbrain-aio dub19/gbrain-aio https://hub.docker.com/r/dub19/gbrain-aio bridge sh false https://github.com/wgross19/gbrain-aio/issues https://github.com/wgross19/gbrain-aio Vanilla GBrain all-in-one for Unraid. One s6 container runs PostgreSQL 17 + pgvector, the official GBrain HTTP server, a Caddy TLS reverse proxy, the GBrain job supervisor, and in-container maintain (autopilot every 30 minutes, nightly dream, weekly doctor). Postgres listens on loopback only and is never published. Agents connect only through the MCP endpoint, never to Postgres. First run: 1. Set POSTGRES_PASSWORD (alphanumeric) and GBRAIN_ADMIN_BOOTSTRAP_TOKEN (32+ chars, alphanumeric + _-). Generate a token with: head -c 32 /dev/urandom | base64 | tr -d '+/=' | head -c 48 2. Set GBRAIN_LAN_BIND to your Unraid host LAN IP and GBRAIN_PUBLIC_URL to https://<that IP>:3132. Both are local-network only. 3. Create an empty brain folder (e.g. /mnt/user/my-brain) and set Brain Path to it. Set Source Name to the folder's name (e.g. my-brain). 4. Start the container, then open https://<lan>:3132/admin/ and paste the bootstrap token. The container inits the brain, git-inits if needed, registers the source, and queues a sync. No docker exec required. 5. Trust the generated CA once (caddy/certs/ca.pem) on any phone or WebView. Advanced users can point OLLAMA_BASE_URL at a local Ollama for embeddings and openai-compat chat, or add a provider API key (Anthropic, OpenAI, Gemini, DeepSeek, Groq, Voyage) in the advanced fields. Leave optional URL, budget, and toggle fields empty to keep them off. ### 2026-08-18 - Generated from CHANGELOG.md during release preparation. Do not edit manually. - Lock self-sufficient gbrain-aio maintain spec - Auto-init brain on first boot + document config gotchas - Self-sufficient first-boot, autopilot, dream, and doctor (#2) AI Tools:Utilities https://[IP]:[PORT:3132] https://raw.githubusercontent.com/wgross19/awesome-unraid/main/gbrain-aio.xml https://raw.githubusercontent.com/wgross19/awesome-unraid/main/icons/gbrain.png gbrain brain knowledge graph AI agent memory Docker with Compose. A LAN IP you control. Optional: a local Ollama at http://<lan>:11434 for embeddings and chat. Support wgross19 on GitHub Sponsors. https://github.com/sponsors/wgross19 bridge 3132 3132 tcp /mnt/user/appdata/gbrain-aio/data/postgres /data/postgres rw /mnt/user/appdata/gbrain-aio/gbrain-home /var/lib/gbrain rw /mnt/user/appdata/gbrain-aio/caddy /config/caddy rw /mnt/user/my-brain /my-brain rw 3132 /mnt/user/appdata/gbrain-aio/data/postgres /mnt/user/appdata/gbrain-aio/gbrain-home /mnt/user/appdata/gbrain-aio/caddy /mnt/user/my-brain gbrain gbrain my-brain 99 100 ollama ollama deepseek-v4-flash:cloud