MonkeyCode: a self-hostable AI work platform for teams
AI coding platform for teams
At a glance
- What is it?
- MonkeyCode by Chaitin is an open-source, AGPL-licensed AI work platform for teams, presented in its README as 百智办公 · MonkeyAI, covering office, programming and design tasks with team resource sharing, central management and private deployment.
- Who is it for?
- Consider MonkeyCode if you lead an engineering team that wants AI coding centrally managed inside your own network, with shared AI resources and central management. Try the demo server first, then read the AGPL-3.0 terms and the deployment sizing before self-hosting.
- Can I use it commercially?
- Yes, with strict conditions. AGPL-3.0 is a network copyleft licence: if people use a modified version over a network, for example as a hosted service, you must offer them its source code under the same licence.
- Is it still maintained?
- Yes. The repository last received commits 1 day ago.
- What is it written in?
- Mainly TypeScript, according to GitHub's language statistics.
Answers come from the project's GitHub data, last synced on November 13, 2026, and from our analysis. They are not legal advice.
Star history
- chaitin/MonkeyCode5,199 ★ · +493
| Repository | 2026-09-15 | 2026-11-13 |
|---|---|---|
| chaitin/MonkeyCode | 4.7k | 5.2k |
493 Stars in the last 59 days, measured from the daily GitHub snapshot. Compare with other projects
Editorial analysis
What MonkeyCode is, and how it differs from vibe coding tools
The README presents the project as 百智办公 · MonkeyAI, a team AI workbench and enterprise-grade open-source AI office management platform: you describe a request in natural language and AI completes office, programming and design tasks, with team resource sharing, unified management and private deployment.
That framing shapes everything else. You can deploy it on your own server, and an enterprise management panel manages the team's AI resources, access permissions and usage centrally. The people it is for are R&D leads and platform teams who want AI coding governed in one place, not thirty developers each configuring their own tool.
Cloud development environments and the task workflow
The README lists clients for Web, Windows x64, macOS (Apple Silicon and Intel) and Linux x64, all connecting to the same team workspace; Android, iOS, Linux ARM64 and HarmonyOS desktop are listed as coming soon. Cloud computers are offered only in the paid tier, not the free one.
Model support, including Chinese models
The README names no specific models. Teams can connect their own model services, link business tools through MCP connectors, and combine knowledge bases, skills, experts and rules to fit their workflow, sharing these resources across the team. After private deployment, team data stays on your own servers, but content is still sent to any external model or tool you configure.
Where MonkeyCode leads and where it does not, per its own table
The README contains no comparison with Cursor, Claude Code or Codex. Its management table lists four capabilities: team resource sharing, resource usage and billing, permission control and usage auditing, and team usage statistics.
Deploying MonkeyCode yourself
For teams that want it on their own infrastructure, the README gives a lightweight configuration of 1 CPU core and 1 GB of RAM, to be adjusted for team size, storage capacity and task load.
The online installation is a single command:
bash -c "$(curl -kfsSL https://release.monkeycode-ai.com/public/monkeyai-install.sh)"The README points to fuller deployment documentation for other methods, configuration and operations. As with any script piped from a URL into a shell, read what it does before running it on a production host. The README says team data is kept on your own server, though content is still sent to any external model or tool you configure.
Licence, releases and support
MonkeyCode is licensed under AGPL-3.0. That is a strong copyleft licence, and the network clause matters for a platform you might offer to your own users: if you modify MonkeyCode and expose it over a network, the AGPL's terms about providing source apply. Any team building on it should read the licence with that in mind rather than treating it like a permissive open-source project.
The recent releases follow a date-based version scheme: v26072801 on 2026-07-28, v26072101 on 2026-07-21 and v26072001 on 2026-07-20, and the last push to the repository was on 2026-11-02, so development is active. The repository is a monorepo, with backend, frontend, desktop, mobile and browser-extension directories among others. Support runs through the product documentation, enterprise consulting, GitHub issues and a WeChat group.
Editorial conclusion
Consider MonkeyCode if you lead an engineering team that wants AI coding centrally managed inside your own network, with shared AI resources and central management. Try the demo server first, then read the AGPL-3.0 terms and the deployment sizing before self-hosting.
Frequently asked questions
What is MonkeyCode used for?
MonkeyCode, now presented as 百智办公 · MonkeyAI, is an open-source AI workbench for teams. You describe a request in natural language and AI completes office, programming and design tasks, with central management of AI resources, permissions and usage, and optional private deployment.
Do you have to pay to use MonkeyCode?
There is a free tier at ¥0 with up to 10 seats, and a paid tier priced by consultation that adds cloud computers and technical support. The project is open source under AGPL-3.0, so you can also self-host it.
Is MonkeyCode safe to run on private code?
With private deployment, team data is kept on your own servers, but when you use external models or tools the relevant content is still sent to the services you configure. The code is open source under AGPL-3.0 and can be inspected.
Official sources
Was this useful?