An open-source AI coding agent that handles web apps, data science pipelines, test generation, and more. Just describe what you need — AACode writes production-ready code with tests, powered by DeepSeek and any LLM of your choice.
Simple core logic that trusts model capabilities instead of complex frameworks.
Dynamic discovery with Markdown files as primary storage for context.
Flexible system access through intelligent safety guardrails.
Reduction strategies inspired by Cursor and Manus for optimal token usage.
All blocking operations are async for maximum performance.
Atomic tools, management tools, and Skills in a three-layer architecture.
Comprehensive command and path security checks built in.
Support for custom tools, MCP resources, and multiple model backends.
Prefer a graphical interface? Try AACode Desktop.
Install via pip, then initialize your configuration.
# Install
pip install aacode
# Initialize configuration
aacode initConfigure your LLM provider (supports DeepSeek, OpenAI, and more).
export LLM_API_KEY="your-api-key"
export LLM_API_URL="https://api.deepseek.com/v1"
export LLM_MODEL_NAME="deepseek-chat"Point to your project directory and describe what to build.
aacode run -p /path/to/project "Create a calculator program with tests"Download the desktop app, install Python 3.12+, and start coding visually.
AACode Desktop requires Python to run the backend service. Download from python.org or use Homebrew.
# macOS (Homebrew)
brew install python@3.12
# Verify
python3 --versionInstall the Python package via pip.
pip install aacodeRun aacode init or configure API keys in the Desktop settings page.
Download from the section above, install, and start coding. Select your project directory and describe your task.
Core Components of the AACode Engine
Task decomposition and coordination
Intelligent think-act loop
File-based context management
Atomic, management & Skills layers
Command & path security checks
Flexible configuration management