Skip to main content

OtoDock — Collaborative Agents

A team of AI agents that work together, and alongside your people — running on infrastructure you control.

Ninety seconds of OtoDock at work — sound on. (watch on otodock.io)

OtoDock is a self-hosted platform for running a team of AI agents. You connect the AI subscriptions and API keys you already have, and OtoDock gives you a polished dashboard to chat with agents, automate work on a schedule, hold multi-agent meetings, and plug into the tools you use every day — all on hardware you control, with your data and credentials never leaving your reach.

Built for teams — and great for individuals​

OtoDock is designed for organizations that want AI woven into how the whole company works: give every team and role its own agents, then let them handle routine work, automate processes, and keep an eye on things around the clock. With one platform you can stand up:

  • Personal assistants for each employee
  • Customer support agents
  • Social media and content agents
  • Business analyst and reporting agents
  • Monitoring and system-administration agents
  • Coding agents for your engineers
  • …and as many specialized agents as your work needs

It works just as well for an individual who wants a capable assistant and automation on their own terms.

note

OtoDock gives you the platform to build and run these agents today. It ships with one ready assistant; you create the rest, or install them from the community catalog as it grows.

What makes it work​

  • The agents that actually get work done. OtoDock runs your real work on the two most capable AI agents available — Anthropic's Claude Code and OpenAI's Codex. They were built for software engineering, one of the hardest things to automate well — and that same depth makes them excellent at complex work of every kind: research, analysis, operations, content, and support. You connect your own Claude or ChatGPT subscription (or API keys) directly, and OtoDock runs them as full agents with the tools, files, and memory they need.
  • A real dashboard. A fast, live web dashboard drives those agents for you — watch their work stream in real time (text, reasoning, tool calls, file edits, plans, to-do lists), chat, run background tasks, hold meetings, and manage everything from one place.
  • Bring your own AI. Use your Claude or ChatGPT subscriptions, provider API keys, or local models — OtoDock routes each conversation to the right engine.
  • Real capabilities. Documents and files, web browsing, scheduled tasks, event triggers, voice, long-term memory, and a growing catalog of integrations.
  • Secure by default. Every agent runs in a strict sandbox: its filesystem and network access are locked down, so it can't roam your machine or scan your network. You decide exactly which folders and which endpoints each agent can reach. See Security.

Run it your way​

  • Self-hosted — install OtoDock on your own server. You hold the data and the keys. This is what most of these docs cover.
  • Cloud (coming soon) — we run the platform for you. Same agents, same dashboard, no ops.

Start here​

Fair source

OtoDock is fair source — the full source is available to read, run, and modify under a fair-source license. See otodock.io/fair-source for what that means and what you can do with it.

Looking for product info, pricing, or your account? Head to otodock.io.