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.
Documentation/Build with OwnPilot
THE OWNPILOT FIELD GUIDE

From a request to a routine

Visual workflows, scheduled tasks, triggers, plans and proactive autonomy.

OwnPilot v0.8.3 · Source-verified guide

Visual workflows

OwnPilot includes a visual workflow builder for connecting steps and tools. Workflows can include agent execution; Claw integration lets a workflow start a dedicated autonomous runtime.

Use explicit inputs and completion conditions. Test a workflow manually before attaching a schedule or external trigger.

Triggers and heartbeats

Triggers support schedules, events, conditions and webhooks. Natural-language scheduling can convert requests such as “every weekday at 9am” into cron schedules. Confirm the resulting schedule and timezone in your instance.

Goals and plans

Goals can be decomposed into steps with progress tracking and next-action suggestions. Multi-step plans include checkpoints, retries and timeout handling. A clear goal makes a better boundary than an open-ended instruction to keep working.

The pulse engine

The proactive pulse engine gathers context, evaluates signals and can take actions on an adaptive timer. Configurable directives and preset templates shape its behavior.

Review autonomy, tool approvals and spending limits before enabling proactive work. A scheduled agent is still using the model providers and external services you configured.

FOLLOW THE SOURCE

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

Product README