moerasermax

Tkflyc AI CLI — AI skill for Claude Code

AI community

Run Claude Code, Codex, Antigravity and any OpenAI-compatible API as MCP tools with background jobs — registry architecture, circuit breaker, honest return values.

How to install Tkflyc AI CLI

This entry records only its repository, not the path inside it, so there is no exact command to give. Open moerasermax/tkflyc-ai-cli and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Tkflyc AI CLI does

Run Claude Code, Codex, Antigravity and any OpenAI-compatible API as MCP tools with background jobs — registry architecture, circuit breaker, honest return values.

Alternatives in AI

Ralph For Claude Code — by Frank Bria - An autonomous AI development framework that enables Claude Code to work iteratively on project 8k ★
WindsurfAPI — Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A 3k ★
Vllm Mlx — High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon 1.5k ★

README

ai-cli-mcp

[![CI](https://github.com/moerasermax/tkflyc-ai-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/moerasermax/tkflyc-ai-cli/actions/workflows/ci.yml) [![npm](https://img.shields.io/npm/v/%40tkflyc%2Fai-cli-mcp)](https://www.npmjs.com/package/@tkflyc/ai-cli-mcp) [![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)

Run local AI CLIs — Claude, Codex, Antigravity (`agy`) — and **any third-party OpenAI-compatible API** as MCP tools, with background jobs. Self-maintained from source, built on a registry architecture: adding an agent means adding one file.

Requires Node `^20.19.0 || >=22.12.0`.

完整中文文件（環境變數、設定檔、每個工具的細節）見 **[README.zh-TW.md](README.zh-TW.md)**. The Chinese document is the exhaustive reference; this page covers the design and the parts you need to get running.

Quick start

From npm — nothing to build:

claude mcp add ai-cli -s user -- npx -y @tkflyc/ai-cli-mcp

From source — if you intend to change it:

git clone https://github.com/moerasermax/tkflyc-ai-cli
cd tkflyc-ai-cli
npm install     # triggers build via the prepare script and produces dist/
claude mcp add ai-cli -s user -- node "$PWD/dist/server.js"

`dist/` is not version-controlled, so the source install has to build before first use. `npm install` runs it through the `prepare` script, so a separate `npm run build` is normally unnecessary.

What it does

Each supported CLI becomes a tool you can call from an MCP client. Jobs run in the background: `run` returns a PID immediately, and `list_processes`, `peek`, `wait` and `get_result` observe it while it works. Three entry points — the MCP server, the `ai-cli` command line, and the detached file-backed runner — are equivalent in behavior; they differ only in where job state lives.

Architecture

src/
├─ agents/                one file per AI — this is the extension point
│   ├─ types.ts               AgentDefinition, the core contract
│   ├─ registry.ts