you-want

you-want / mini-cc

Public

🚀 一个轻量级的多语言 AI 编程智能体，内置声明式终端 UI、原生 MCP 插件生态与无缝的 Tool-Use 循环

mini-cc.raingpt.top
73
8
100% credibility
Found Apr 24, 2026 at 73 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Mini-cc is a multi-language open-source framework that powers lightweight AI coding agents capable of reading/writing files and executing shell commands via various large language models.

How It Works

1
🔍 Discover your new coding helper

You stumble upon mini-cc on a coding site, a friendly AI buddy that helps write and fix code by chatting.

2
📥 Bring it home to your computer

You grab the ready-made version for your favorite setup and place it in a folder.

3
🔗 Connect a smart brain

You link it to a thinking service so it can understand and respond to your ideas.

4
💬 Start a conversation

You open it and type your first request, like 'make a hello world file'.

5
✨ Watch the magic happen

It thinks step-by-step, reads files, writes code, runs tests, and shows you everything live.

6
🔄 Keep building together

You chat more to tweak code, check files, or run commands, feeling like you have a smart partner.

🎉 Projects come alive effortlessly

Your coding dreams turn into working files and apps, faster and with fun surprises like a virtual pet.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 73 to 73 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is mini-cc?

mini-cc is a lightweight terminal-based AI programming agent that lets you delegate coding tasks like file editing, bash commands, and git ops via natural language. Built primarily in TypeScript with ports in Go, Python, and Rust, it supports Anthropic (Claude MCP tool use) and OpenAI-compatible models (Qwen, DeepSeek) in a seamless tool-use loop. Developers get a REPL-style CLI for quick prototyping, plus a declarative Ink/React UI and native MCP plugin ecosystem for extending with tools like mcp github copilot vscode integrations.

Why is it gaining traction?

It stands out for its multi-language implementations—pick TypeScript for UI polish, Rust for speed, or Go/Python for simplicity—while packing MCP tool use prompts that rival claude mcp tool use or mcp vs tool use setups. The hook is effortless multi-round agent loops with safety sandboxes, detailed docs on mcp github docs and mcp github server list, plus easy extensibility via mcp github n8n or mcp github typescript plugins. No bloat: compiles to single binaries, streams reasoning, and handles long contexts without token explosions.

Who should use this?

Backend devs automating build scripts or debugging via bash in VSCode (mcp github copilot vscode), full-stack teams prototyping with clion use mcp tool or mcp github copilot intellij, or AI tinkerers exploring mcp github python agents. Ideal for solo hackers needing a local copilot alternative without cloud lock-in, or educators teaching anthropic mcp tool use loops.

Verdict

Grab it if you're into MCP ecosystems—solid docs and tests make it a great learning tool despite 73 stars and 1.0% credibility score signaling early maturity. Production-ready for scripts, but watch for plugin stability in mini cc addons.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.