Oh My Kimi
Verified agent runtime for Kimi Code. Stable daily-use core with alpha orchestration surfaces; release-gated and evidence-gated workflows. | Kimi Code向け検証済みエージェント実行基盤。日常利用コアは安定、オーケストレーション面はalpha。
What is Oh My Kimi?
Oh My Kimi is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to verified agent runtime for kimi code. stable daily-use core with alpha orchestration surfaces; release-gated and evidence-gated workflows. | kimi code向け検証済みエージェント実行基盤。日常利用コアは安定、オーケストレーション面はalpha。
Verified agent runtime for Kimi Code. Stable daily-use core with alpha orchestration surfaces; release-gated and evidence-gated workflows. | Kimi Code向け検証済みエージェント実行基盤。日常利用コアは安定、オーケストレーション面はalpha。
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Verified agent runtime for Kimi Code. Stable daily-use core
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx oh-my-kimiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Oh My Kimi
Oh My Kimi (OMK) is a verified agentic runtime and MCP server for Kimi Code that provides a stable foundation for autonomous coding tasks, DAG-based task planning, and multi-agent orchestration. It supports routing across multiple AI providers including Kimi, Claude Code, DeepSeek, Qwen, and OpenRouter, with authority scoping for read, write, shell, and merge permissions and evidence-gated workflows that require command output, diffs, or review proofs before proceeding. Developers who want a production-ready, audit-friendly coding agent framework with deterministic replay artifacts will find OMK particularly useful.
Prerequisites
- Node.js 18 or later and npm/npx
- API key for Kimi Code or another supported provider (Claude Code, DeepSeek, Qwen, OpenRouter)
- Git for repository operations that the agent will perform
- An MCP-compatible client or use OMK's own CLI directly
- Basic familiarity with DAG-based task planning concepts
Install Oh My Kimi globally
Install the open-multi-agent-kit package globally to get the omk CLI available on your PATH.
npm install -g open-multi-agent-kitInitialize a new OMK project
Run omk init in your project directory to create the necessary configuration files and directory structure.
omk initRun the doctor check
Use omk doctor to verify your environment, check provider connectivity, and confirm all required dependencies are available.
omk doctorRun a task with dry-run first
Use --dry-run to preview the DAG plan and input envelopes that OMK would execute before actually running the agent. This lets you verify scope and authority before committing.
npx -y -p open-multi-agent-kit omk do "review this repo for release risk" --dry-run --jsonStart an interactive chat session
Launch the interactive chat interface to communicate with your configured AI provider through the OMK runtime.
omk chatOh My Kimi Examples
Client configuration
Add OMK as an MCP server in your Claude Desktop configuration to use it as a coding agent tool provider.
{
"mcpServers": {
"oh-my-kimi": {
"command": "npx",
"args": ["oh-my-kimi"]
}
}
}Prompts to try
Example tasks and queries for the OMK agentic runtime.
- "Review this repository for release risk and list any blocking issues."
- "Generate a DAG plan for adding JWT authentication to this Express app."
- "Run the test suite and fix any failing tests, showing diffs before applying."
- "Refactor the database layer to use connection pooling — show me the plan first."
- "Summarize all changes made in the last sprint using the git log."Troubleshooting Oh My Kimi
omk doctor reports a provider connection failure
Ensure your API key for the configured provider is set in your environment or OMK config. For Kimi Code, set the appropriate key variable. Run `omk doctor` again after setting the key to re-validate the connection.
DAG compilation fails with missing input envelope error
Review the task description for ambiguous scope. OMK requires well-defined task inputs before compiling a DAG. Use --dry-run --json to inspect what inputs are expected and provide more specific task parameters.
Agent executes changes without showing a diff first
Configure evidence requirements in your OMK project settings to require diffs or artifacts before merge operations. Use the --dry-run flag during development to always preview planned actions before execution.
Frequently Asked Questions about Oh My Kimi
What is Oh My Kimi?
Oh My Kimi is a Model Context Protocol (MCP) server that verified agent runtime for kimi code. stable daily-use core with alpha orchestration surfaces; release-gated and evidence-gated workflows. | kimi code向け検証済みエージェント実行基盤。日常利用コアは安定、オーケストレーション面はalpha。 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Oh My Kimi?
Follow the installation instructions on the Oh My Kimi GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Oh My Kimi?
Oh My Kimi works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Oh My Kimi free to use?
Yes, Oh My Kimi is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Oh My Kimi Alternatives — Similar Coding Agents Servers
Looking for alternatives to Oh My Kimi? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Oh My Kimi in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Oh My Kimi?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.