CopilotKit OpenBot is an open source template for AI coworkers you run on infrastructure you own. It is not a hosted product with a signup page. You clone it, customize it, and bring your own AG-UI agents. As of the official README, the project is still Alpha and under active development.
That framing matters. A lot of writeups make OpenBot sound like a polished afternoon install that ships ready-made enterprise bots. The real picture is sharper and more limited: a customizable agent app shape, computer use per bot, governance hooks, and example coworkers you adapt. Below is what it is, what you need to run it, and when it is (and is not) the right call.
What OpenBot is (and is not)
OpenBot gives your company a ChatGPT-like surface that runs on your stack. Employees chat with bots. Those bots can use tools, browse, and work through multi-step jobs. The difference that matters: it is designed so you own the runtime, the logs, and the policy layer.
It is:
- A template, not a SaaS. There is no hosted CopilotKit OpenBot signup. You clone and customize.
- Built around AG-UI agents. You bring agents from stacks like LangGraph, Mastra, CrewAI, Pydantic AI, Google ADK, or hand-written agents that speak AG-UI.
- Oriented to AI coworkers: bots that act inside company systems with clearer boundaries than a naked chat window.
It is not:
- A finished product you turn on for the whole company with one click.
- A promise that "free" means zero cost beyond cloning. You still need runtime pieces and a model key (details below).
AG-UI first: bring your own agent
OpenBot's center of gravity is the agent you connect, not a single locked-in model brand.
AG-UI (Agent-User Interaction) is the protocol lane the project centers on. In plain terms: your agent talks to the OpenBot app through a shared interface, so the chat UI, approvals, and tool gateway can stay stable while you swap agent frameworks.
That is why official docs list several agent options instead of one proprietary brain. If you already have an agent harness at work, OpenBot is closer to "put a company-facing app around it" than "throw away your stack and start over."
Computer per agent, not one shared browser tab
Each bot is meant to get its own computer boundary: its own container, its own Chromium session, and its own logins. That is stronger than "a sandboxed browser somewhere on a shared host."
Why it matters for real work:
- One bot's messy login state should not bleed into another bot's session.
- You can reason about permissions per coworker, not as one giant shared desktop.
- A fail-closed gateway sits in front of tools, so actions that are not allowed should stop before they run.
OpenBot also leans on CopilotKit Intelligence for thread and related storage (with a free plan available, and self-host options). Treat that as part of the runtime story, not an optional footnote.
What you actually need to run it
From the official requirements direction (confirm on the current README before you start):
- Bun 1.3+
- Docker
- A CopilotKit Intelligence project / license (free plan exists; you can also self-host)
- A model key for whatever model your agents call
Demo path vs production path:
- Docker Compose is the common path for a local or demo spin-up.
- Helm is the production-oriented path called out on the product site when you move past a laptop demo.
If someone tells you it is "just MIT and you're done," that undersells the Intelligence + model key + ops work. The template may be open. Running it still has moving parts.
Thirteen example coworkers (fintech set)
The README now ships thirteen example coworkers, oriented around a fintech set, not a vague "enterprise coworkers" pitch. Treat them as starting points you customize, not as certified bots for your compliance team.
That growth is useful for learning shape and prompts. It is not a substitute for your own roles, tools, and approval rules.
A realistic setup path
- Read the Alpha callout and the "template, not a product" note on the GitHub README.
- Clone the repo and follow the current Compose quickstart for a demo.
- Connect an AG-UI agent you already understand (or one of the documented options).
- Confirm Intelligence project/license setup and your model key.
- Create one bot with a tight tool allowlist and watch the computer boundary (container + browser) before you add more bots.
- When you outgrow the demo, look at Helm and your company's usual production checklist (secrets, networking, audit retention, who can approve risky tools).
Skip the fantasy where you paste one command and wake up with a governed workforce of agents. Alpha templates do not work that way.
When OpenBot is a good fit
Choose it when:
- You want coworkers on infrastructure you control.
- You already care about agent frameworks and want a company UI around them.
- You need per-bot computer isolation and a place to hang governance, not only chat.
Look elsewhere (or wait) when:
- You need a managed SaaS with support SLAs tomorrow.
- Your team cannot own Docker, secrets, and model spend.
- You expected a finished product catalog instead of a template plus examples.
How this compares to "just use a closed chat app"
Closed chat apps are fast to try. They are often weak when you need your data residency story, your tool gateway, and your own agent harness under one roof.
OpenBot flips that tradeoff: more ownership, more setup, Alpha sharpness. Grok Bot and similar computer-use agents are useful comparisons when you care about desktop control and agent autonomy, but they are different products with different hosting stories. Do not treat any of them as drop-in clones of each other.
If you are following AI coworker and agent tooling more broadly, our AI tools coverage rounds up more breakdowns like this one, from AG-UI agent frameworks to browser and computer-use agents.
Want a structured way to practice?
If you are exploring AI coworkers and self-paced learning paths (agents, automation, content) without a fixed cohort, look at how 4Geeks AI Flex is structured: ready-made paths, an AI tutor, and mentorship you can start when you are ready.
Sources to recheck before you ship a pilot
- GitHub: CopilotKit/openbot (Alpha badge, template callout, requirements, example pack)
- Product page: copilotkit.ai/openbot (positioning, Compose vs Helm notes)
README details move while the project is Alpha. Re-read those two pages the day you install.
If you are looking for structured AI training, review our AI programs side by side: length, level and outcomes.