OwnPilot.
GitHub
Your first flightInstall OwnPilot, connect a model, and give your assistant its first task.InstallationDocker, source development, prerequisites and first-run checks.A system you can understandFollow a request from your interface through the gateway to models, tools and storage.Meet your working crewChat agents, Claw runtimes, Soul identities and multi-agent crews.Give your AI useful handsBuilt-in tools, MCP servers, extensions, skills and your own CLI tools.Your choice of intelligenceCloud providers, aggregators, local models and routing strategies.From a request to a routineVisual workflows, scheduled tasks, triggers, plans and proactive autonomy.Talk where you already areWeb chat, Telegram, WhatsApp, voice and real-time feedback.A memory for your working lifeNotes, tasks, goals, contacts, custom tables and persistent memory.Ownership, with clear boundariesData flow, authentication, tool approvals, isolation and deployment responsibilities.Make it your ownEnvironment variables, Config Center, model settings and safe defaults.Give OwnPilot a reliable homeVolumes, HTTPS, authentication, backups and upgrading a self-hosted instance.Build around the gatewayHTTP APIs, streamed responses, WebSocket events and MCP.
OWNPILOT DOCUMENTATIONESC to close
Documentation/Connect
THE OWNPILOT FIELD GUIDE

Your choice of intelligence

Cloud providers, aggregators, local models and routing strategies.

OwnPilot v0.8.3 · Source-verified guide

Native providers

The README documents direct integrations for OpenAI, Anthropic, Google and Zhipu. Configure credentials in Settings → Config Center. Streaming, tool use and provider-specific capabilities depend on the selected model and configuration.

Aggregators and compatible endpoints

Together AI, Groq, Fireworks, DeepInfra, OpenRouter, Perplexity, Cerebras and fal.ai appear in the documented aggregator catalog. OpenAI-compatible endpoints allow additional providers to connect.

A compatible API shape does not guarantee identical model behavior. Check tool calling, context limits and any provider-specific restrictions for your chosen model.

Local models

Ollama, LM Studio, LocalAI and vLLM are documented local options. OwnPilot supports local network discovery for compatible runtimes. Start the model service separately, then configure its reachable endpoint.

When the gateway runs in Docker, localhost refers to the container. Use a host address reachable from that container according to your Docker platform and network setup.

Routing and fallbacks

Routing strategies include cheapest, fastest, smartest, balanced and fallback. Per-process model selection lets chat, channels and the pulse engine use different configured choices.

Costs, availability and model capabilities are properties of your provider. Verify them with that provider before setting unattended budgets.

FOLLOW THE SOURCE

Based on the product’s documented behavior. Check the source for your deployed version.

Product README
PreviousGive your AI useful handsUp nextFrom a request to a routine