AI-powered coding assistant with a beautiful web interface, powered by free Groq API
Project description
Ameck Copilot ๐ค
AI-powered coding assistant with a beautiful web interface, powered by FREE Groq API.
โจ Features
- ๐ Lightning Fast - Powered by Groq's ultra-fast inference
- ๐ฐ Completely FREE - Uses Groq's free tier (Llama 3.3 70B)
- ๐จ Beautiful UI - Modern, responsive web interface
- ๐ฌ Chat Interface - Natural conversation with context awareness
- ๐ Code Analysis - Explain, review, optimize, fix, and document code
- โก Code Generation - Generate code from natural language descriptions
- ๐ Multiple Models - Choose from various free models
๐ฆ Installation
pip install ameck-copilot
๐ Quick Start
1. Get your FREE Groq API key
- Visit console.groq.com/keys
- Sign up for a free account
- Create a new API key
2. Run Ameck Copilot
ameck-copilot
On first run, you'll be prompted to enter your API key. It will be saved securely for future use.
3. Open in browser
The app will automatically open at http://127.0.0.1:8000
๐ Usage
Commands
# Start the server (default)
ameck-copilot
# Start on a specific port
ameck-copilot run --port 3000
# Configure API key
ameck-copilot setup
# Show current configuration
ameck-copilot config
Environment Variables
You can also set the API key via environment variable:
export GROQ_API_KEY=gsk_your_api_key_here
ameck-copilot
๐ฏ Features
Chat
Have natural conversations about code. Ask questions, get explanations, and receive coding help.
Modes
The assistant now supports multiple modes to tailor behavior:
- Ask โ General Q&A and conversational assistance (default)
- Agent โ Proposes prioritized actions, outlines goals, and asks clarifying questions when needed
- Edit โ Produces edits/patches or unified diffs for code and text
- Plan โ Generates concise, actionable plans with numbered steps and acceptance criteria
Code Analysis
- Explain - Get detailed explanations of code
- Review - Get code quality feedback
- Optimize - Get performance improvements
- Fix - Identify and fix bugs
- Document - Add documentation
- Test - Generate unit tests
Code Generation
Describe what you want to build and get production-ready code with proper error handling.
๐ค Available Models
๐ข Publishing
This project can be published in three distribution channels:
- PyPI (Python package) โ installable via
pip install ameck-copilot. - VS Code Marketplace โ a minimal extension is included in
vscode-extension/that opens the local web UI or starts the server. - GitHub โ recommended repo:
https://github.com/QuantBender/ameck-copilot(I can create it if you provide a token).
See RELEASE.md for step-by-step publishing instructions and how to add required secrets.
| Model | Description |
|---|---|
| Llama 3.3 70B | Best all-around (default) |
| Llama 3.1 8B | Fast & lightweight |
| GPT-OSS 120B | OpenAI's open model |
| GPT-OSS 20B | Smaller OpenAI model |
| Llama 4 Scout 17B | Latest Llama 4 |
| Qwen 3 32B | Alibaba's model |
๐ ๏ธ Development
Clone and install locally
git clone https://github.com/ameck/ameck-copilot.git
cd ameck-copilot
pip install -e .
Run in development mode
ameck-copilot run --host 0.0.0.0 --port 8000
๐ Project Structure
ameck-copilot/
โโโ src/
โ โโโ ameck_copilot/
โ โโโ __init__.py
โ โโโ cli.py # CLI entry point
โ โโโ app/
โ โ โโโ main.py # FastAPI application
โ โ โโโ config.py # Configuration
โ โ โโโ models.py # Pydantic models
โ โ โโโ routes/ # API routes
โ โ โโโ services/ # Business logic
โ โโโ static/ # Frontend files
โโโ pyproject.toml
โโโ README.md
๐ License
MIT License - see LICENSE for details.
๐ Acknowledgments
- Groq - For providing free, fast AI inference
- Meta - For Llama models
- FastAPI - For the amazing web framework
Made with โค๏ธ by Ameck
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ameck_copilot-1.0.1.tar.gz.
File metadata
- Download URL: ameck_copilot-1.0.1.tar.gz
- Upload date:
- Size: 29.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4be376fdab0596e06307134e391630912419a21534dd5fb990d5b4b2b50dd74a
|
|
| MD5 |
839211efb48f7fc91a09b0a98adb4dad
|
|
| BLAKE2b-256 |
1b6a9765d6530f6b188e214c2d99df9eb3e8cfe865fdaba4459e73ca9fbab2d6
|
File details
Details for the file ameck_copilot-1.0.1-py3-none-any.whl.
File metadata
- Download URL: ameck_copilot-1.0.1-py3-none-any.whl
- Upload date:
- Size: 33.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bfe53a64c03379dbaa79140ccaf63a87d015084973fbf77e67a5dc67d8f2f953
|
|
| MD5 |
2df8dd10531e62edf9919fc01f5cf6e5
|
|
| BLAKE2b-256 |
2e24653175f7ee120f1f4ef1160ed27e9f6b2a3abb63beefbc41aa23683c5ca5
|