Skip to main content

A lightweight AI pair programming agent in Python (Compatible with @you-want/mini-cc)

Project description

mini-cc (Python Edition)

you-want-mini-cc is the Python port of the lightweight AI pair programming agent @you-want/mini-cc. It provides a seamless, terminal-based pair programming experience powered by Large Language Models (LLMs) such as Claude 3.5 Sonnet and Qwen.

Installation

pip install you-want-mini-cc

Quick Start

Before running, you need to configure your LLM provider credentials. The agent supports both OpenAI-compatible APIs and Anthropic.

  1. Create a .env file in your working directory (or set environment variables globally):
# For OpenAI Compatible Models (e.g., Qwen, DeepSeek)
PROVIDER=openai
OPENAI_API_KEY=your_api_key_here
OPENAI_BASE_URL=https://api.your-provider.com/v1
MODEL_NAME=qwen3.6-plus

# OR For Anthropic Models
PROVIDER=anthropic
ANTHROPIC_API_KEY=your_api_key_here
MODEL_NAME=claude-3-7-sonnet-20250219
  1. Run the CLI in your terminal:
mini-cc

Features

  • Pure Python & Asyncio: Fully asynchronous architecture for blazing-fast non-blocking I/O.
  • Agentic Loop: Built-in BashTool, FileReadTool, FileWriteTool for autonomous coding and execution.
  • Security Sandbox: Built-in bash execution wrapper stripper and destructive command interception.
  • High-fidelity Terminal UI: Supports dynamic ANSI-rendered banners and streaming responses.
  • MCP Support: Connects seamlessly with Model Context Protocol (MCP) plugins via stdio.

Usage

Inside the mini-cc> prompt, simply ask the agent to perform tasks:

"Read the src/main.py file and add comments to the functions." "Run tests and fix any failing ones."

Use /help for more built-in commands.

License

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

you_want_mini_cc-1.0.0.tar.gz (29.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

you_want_mini_cc-1.0.0-py3-none-any.whl (36.3 kB view details)

Uploaded Python 3

File details

Details for the file you_want_mini_cc-1.0.0.tar.gz.

File metadata

  • Download URL: you_want_mini_cc-1.0.0.tar.gz
  • Upload date:
  • Size: 29.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for you_want_mini_cc-1.0.0.tar.gz
Algorithm Hash digest
SHA256 fa1de91b87c4b074a244fc8bef56641fe369102181eb61e998377dda417180d0
MD5 07a027a1b78bdb3d4d1853fb5674cbbb
BLAKE2b-256 db8490d6e9e49481ca656da5d29e76ca16e5f391ac4fe31ae8aea068f5502666

See more details on using hashes here.

File details

Details for the file you_want_mini_cc-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for you_want_mini_cc-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 25cf74425e1c4d91cabfa53bfe5720e9d506ab9297968515146aeadba8a38be6
MD5 52b2dedf6ae57fe875e15b7bee5c7a01
BLAKE2b-256 d09c42bf404d6d0dd3389e87e2e0815913dc44860933ff6e382b3c884ac81497

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page