Summary

cc-mini provides an ultra-lightweight scaffolding for AI agents, inspired by Claude Code. It targets developers and power users seeking an extensible framework for building and interacting with AI agents, offering an interactive REPL and autonomous tool-use capabilities. The primary benefit is a concise, yet powerful, foundation for agentic workflows.

How It Works

The core of cc-mini is approximately 1000 lines of Python, enabling an agentic tool loop where the AI autonomously selects and executes tools to complete tasks. It features an interactive REPL with slash command autocomplete, session persistence, and context compression. The system supports Anthropic and OpenAI-compatible API endpoints. Advanced capabilities include Coordinator Mode for parallel background workers, a Tamagotchi-like AI companion ("Buddy"), KAIROS Memory for cross-session context, and a Skills system for one-command workflows like code review or testing. A Sandbox subsystem provides isolated execution for bash commands.

Quick Start & Requirements

Requires Python 3.10+ (3.11+ recommended) and an API key for Anthropic or an OpenAI-compatible provider. Installation can be done via a one-line curl script or by cloning the repository and running pip install -e ".[dev]". API keys are configured via environment variables (e.g., ANTHROPIC_API_KEY or OPENAI_API_KEY with CC_MINI_PROVIDER and OPENAI_BASE_URL). The interactive REPL is launched with cc-mini, and one-shot prompts can be executed directly.

Highlighted Details

• Extremely concise core codebase (~1000 lines of Python).
• Autonomous agentic loop for task completion via tool execution.
• Advanced features: Coordinator Mode for parallel processing, Buddy AI companion, KAIROS Memory, and a Skills framework.
• Compatibility with both Anthropic and OpenAI API endpoints.
• Built-in tools include file read/write, glob, grep, and bash execution with a permission system.

Maintenance & Community

The provided README does not contain information regarding notable contributors, sponsorships, partnerships, or community channels (e.g., Discord, Slack).

Licensing & Compatibility

The README does not specify a software license. This omission makes it impossible to determine compatibility for commercial use or closed-source linking without further investigation.

Limitations & Caveats

The project's license is not disclosed in the README, posing a significant adoption blocker. While advanced features like Coordinator Mode and KAIROS Memory are highlighted, their maturity and stability are not detailed. The "mini" designation suggests it may omit features present in larger, related projects.