Hubzoid is an open-source framework for internal AI agents. Put your team’s knowledge, rules and tools in one shared Hub, then use it in chat, workflows and compatible assistants via MCP. Install: pip install hubzoid. Self-host it. Apache 2.0, team controls included.

Hi Product Hunt! 👋

Hubzoid is an open-source framework for internal AI agents. Bring your team's knowledge, rules, skills and tools into one shared Hub, and reuse that foundation across agents.

⭐ GitHub: https://github.com/hubzoid/hubzoid
📖 Docs: https://hubzoid.com/docs

Use your Hub three ways:

Chat with agents about your team's work.
Run workflows, like a morning briefing.
Connect via MCP from ChatGPT or Claude to use your Hub’s context and authorized tools.

Start with one task and your own material. Your Hub starts with readable Markdown files you can inspect, edit and version in Git. Correct a rule, save it, try again, then share it with teammates.

Fully open source. Apache 2.0. Team controls included. No paid feature gates. Self-host it.
Install:

pip install hubzoid

Need implementation help? Our Build with us service uses the same open-source product.

What's one internal task you'd hand to an agent, and what would it need to know to do it your way?

Hi everyone, I'm Darshika, co-creator of Hubzoid 👋

I'll share a bit about how it feels to use it.

I set up a Hub from our own notes and rules, gave a teammate access to just one agent, and scheduled a daily report. All of it lives in plain Markdown files, so nothing is hidden in a prompt somewhere.

The best part: when the agent gets something wrong, you fix one line and ask again. Everyone on the team gets the corrected answer, and the change is saved in Git.

If you try it today, tell me where setup slowed you down. That's the feedback we want most. I'll be here all day.