MonkeyCode: Enterprise AI Development Platform
An open-source AI development platform for engineering teams, with cloud environments, model management, and team collaboration.
- Source repo
- chaitin/MonkeyCode
- Stars
- ★ 4.8k
- Last updated
- today
- License
- AGPL-3.0
- Primary language
- TypeScript
- FA score
- 33/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platform
- Cost
- Free tier plus a paid hosted plan
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- An enterprise R&D team deploys MonkeyCode inside its internal network to centrally manage AI development workflows while keeping data on-premises.
- Not a fit if
- Developers who need a local IDE or CLI
- Teams that must run fully offline without the vendor cloud
- Teams without 8C/16GB servers for self-hosting
- Source review
- 33/100 · Major gaps 6 safety controls not found
What does this agent do, and when should you use it?
MonkeyCode is an open-source enterprise-grade AI development platform designed for professional engineering teams. Unlike typical vibe coding tools, it integrates development environment management, AI model management, AI task management, and project requirement management. Users can deploy MonkeyCode inside their enterprise network for their R&D team, or use the hosted online environment which includes managed development environments, built-in large language models, and native mobile support. The core code is public on GitHub under the AGPL-3.0 license, and private offline deployment is supported for teams with strict data privacy requirements.
MonkeyCode offers both online and self-hosted modes. In online mode, users access via browser without client downloads or local environment setup. The platform creates cloud development environments where each task runs in a real server-side environment, completing build, test, and preview workflows. It integrates mainstream models like GLM, Kimi, MiniMax, Qwen, and DeepSeek, switchable by task type or manually. Native iOS and Android apps sync data with PC. Self-hosted deployment uses a bash script for installation, with recommended hardware specs for console and development environment hosts.
- An enterprise R&D team deploys MonkeyCode inside its internal network to centrally manage AI development workflows while keeping data on-premises.
- A developer with no local development environment uses the online platform to start AI coding tasks in cloud environments from a browser.
- An engineering leader oversees team AI tasks and requirements, reviewing progress and managing workflows centrally.
- A developer on the go uses the mobile app to check task status and manage files, allowing agents to continue running tasks remotely.
- A team with strict data privacy requirements opts for private offline deployment to keep all code and data local.
How do you install or deploy this agent?
For online use, no installation is needed; visit https://monkeycode-ai.net/ and create an account. For self-hosted deployment, recommended specs: console at least 2C/4GB/40GB, development environment host at least 8C/16GB/100GB. Run: bash -c "$(curl -fsSL 'https://monkeycode-ai.com/online/install')". More methods in the documentation.
How do you use this agent?
After deployment, access the MonkeyCode console via browser, create an account, and log in. Create an AI development task, choose or configure a model, and the system will execute it in a cloud development environment. Monitor progress and manage files in the task workspace, with mobile sync.
What are this agent's strengths and limitations?
- Cloud development environments eliminate local setup overhead.
- Supports multiple Chinese models including GLM, Kimi, MiniMax, Qwen, DeepSeek, with easy switching.
- Native mobile support keeps PC and mobile data in sync.
- Private offline deployment meets strict data privacy requirements.
- Open source (AGPL-3.0) allows auditing and extension.
- Significant server resources required for self-hosted deployment (console min 2C/4GB, host min 8C/16GB).
- Lacks local IDE and CLI integration, limiting local development experience compared to tools like Cursor or Claude Code.
- No code completion feature, offering weaker in-editor assistance.
- Platform functionality is centralized; may require specific deployment environment.
How does this agent compare with similar options?
The README compares MonkeyCode with Cursor, Claude Code, and Codex. MonkeyCode excels in requirement/spec management, cloud development environments, team collaboration, China model support, private deployment, and open source; but lacks local IDE, local CLI, and code completion.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| MonkeyCode: Enterprise AI Development Platform This agent | 33 · Major gaps | Hosted serviceFreemium | ★ 4.8k | today | TypeScript | — |
| Lody | 75 · Good | Self-hosted service | ★ 1.4k | today | TypeScript | Codex · Claude Code |
| Dify | 55 · Major gaps | Self-hosted serviceFreemium | ★ 159k | today | Python | OpenAI API |
| Okto Pulse | 80 · Good | CLIFree | ★ 51 | 2d ago | Python | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows controlled access (checkOpAllowed) and URL whitelist (isAllowedCreateUrl) in browser extension, but no user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, or rollback evidence. Publisher identity unverified, but source attribution clear (chaitin/MonkeyCode).
CI config shows multi-platform builds and tests, but no detailed failure message evidence. Lock files exist (pnpm-lock.yaml, package-lock.json), but dependency availability not verified.
README clearly defines target audience (enterprise R&D teams) and scenarios (online, private deployment), but capability boundaries and trigger precision evidence insufficient. Environment fit shows multi-platform support (Linux/Windows/macOS) and mobile.
Information architecture clear (README, docs links), install notes exist (self-hosted deployment), but known limitations and versioning/changelog missing. License AGPL-3.0, maintenance responsibility via GitHub Actions and community channels.
Output usability not directly verified, but feature descriptions show practical value (cloud dev environments, model support). Cost-benefit not quantified, but open source and free start may lower barriers.
README feature claims lack detailed evidence, but CI config and test files partially support. Cross-source corroboration limited, facts and inferences not clearly separated.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Publisher identity unverified; assess supply chain risks carefully.
- No user confirmation mechanism found; AI tasks may execute actions automatically, requiring human oversight.
- Data flow transparency insufficient; review data collection and transmission.
- Dependency security not assessed; check for dependency vulnerabilities.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v26072801 MonkeyCode v26072801
Release notes excerpt
What's Changed * fix(frontend): remove user message markdown background by @xiaomakuaiz in https://github.com/chaitin/MonkeyCode/pull/909 * fix(frontend): 修复任务技能弹窗内容溢出 by @2379278408 in https://github.com/chaitin/MonkeyCode/pull/903 * 修复启动任务模型选择被数据刷新覆盖 by @2379278408 in https://github.com/chaitin/MonkeyCode/pull/897 * feat(frontend): 支持超长输入转 TXT 附件 by @2379278408 in https://github.com/chaitin/MonkeyCode/pull/886 * 修复：Agent 重启确认弹窗支持键盘方向键切换 by @2379278408 in https://github.com/chaitin/MonkeyCode/pull/911 …View on GitHub ↗ -
v26072101 MonkeyCode v26072101
Release notes excerpt
What's Changed * 修复用户可控地址的内网 SSRF 风险 by @yokowu in https://github.com/chaitin/MonkeyCode/pull/899 * 修复私有地址检测导致的 HTTP/2 协议错配 by @yokowu in https://github.com/chaitin/MonkeyCode/pull/905 * feat(mobile): show workspace upload progress by @xiaomakuaiz in https://github.com/chaitin/MonkeyCode/pull/906 Full Changelog: https://github.com/chaitin/MonkeyCode/compare/v26072001...v26072101 What's Changed * 修复用户可控地址的内网 SSRF 风险 by @yokowu in https://github.com/chaitin/MonkeyCode/pull/899 * 修复私有地址检测导致的 HTTP/2 协议错配 by @yokowu in https://github.com/chaitin/MonkeyCode/pull/905 …View on GitHub ↗ -
v26072001 MonkeyCode v26072001
Release notes excerpt
What's Changed * fix(frontend): support arrow navigation in slash command dialog by @2379278408 in https://github.com/chaitin/MonkeyCode/pull/863 * fix(frontend): add copy action to user messages by @2379278408 in https://github.com/chaitin/MonkeyCode/pull/861 * fix(frontend): restore chat input focus after upload by @2379278408 in https://github.com/chaitin/MonkeyCode/pull/858 * fix(frontend): open workspace links in file preview by @2379278408 in https://github.com/chaitin/MonkeyCode/pull/859 * 修复 VM 空闲回收活动语义并统一回收流程 by @yokowu in https://github.com/chaitin/MonkeyCode/pull/868 …View on GitHub ↗