Give a team's engineering leaders a central place to manage AI-assisted development workflows.
Run AI coding tasks in a cloud environment without setting up a local development machine.
Deploy an AI coding platform privately inside a company network for data privacy reasons.
Switch between multiple AI models like GLM, Kimi, and DeepSeek depending on the coding task.
| chaitin/monkeycode | gothinkster/node-express-realworld-example-app | sourcegraph/cody-public-snapshot | |
|---|---|---|---|
| Stars | 3,790 | 3,791 | 3,794 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | hard | moderate | moderate |
| Complexity | 4/5 | 2/5 | 2/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Self-hosting requires two servers meeting minimum specs (4GB and 16GB RAM) plus configuring AI model access, the hosted online version needs only a browser.
MonkeyCode is an open-source AI development platform built for engineering teams rather than solo hobby coding. It bundles a managed development environment, AI model management, task management, and project requirement management into one place, so a team can hand an AI a requirement and have it carry the work through development and validation instead of stitching several separate tools together. Teams can either run MonkeyCode inside their own company network so engineering leaders can manage AI development workflows centrally, or use the hosted online version, which provides ready-made development environments, several built-in large language models, and native mobile apps for continuing work away from a desktop. Getting started with the online version needs nothing more than a browser and an account, since every task runs in a cloud environment rather than on your own machine, with building, testing, and previewing all handled server-side. MonkeyCode supports multiple mainstream AI models, including GLM, Kimi, MiniMax, Qwen, and DeepSeek, and lets you switch models by task or choose one manually. The project is fully open source, so its code can be audited, forked, and extended by anyone, and it also supports private offline deployment for organizations with strict data privacy requirements. According to the README, self-hosting requires a console server with at least 2 CPU cores, 4 GB of RAM, and 40 GB of storage, plus a separate development environment host with at least 8 CPU cores, 16 GB of RAM, and 100 GB of storage. Compared to tools like Cursor, Claude Code, and Codex, the README highlights MonkeyCode's focus on requirement and specification management, cloud development environments, team collaboration features, and support for models built in China, areas where it says those other tools are weaker. MonkeyCode is licensed under the GNU Affero General Public License version 3.0, and the project offers community support through Discord, WeChat, Feishu, and DingTalk groups.
MonkeyCode is an open-source, enterprise-grade AI development platform that manages cloud coding environments, AI models, and project requirements for engineering teams.
Mainly TypeScript. The stack also includes TypeScript, GLM, Kimi.
AGPL-3.0: you can use and modify the code, but if you run a modified version as a network service, you must release your changes under the same license.
Setup difficulty is rated hard, with roughly 1h+ to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.