Back to directory

CodeCraft

A multi-LLM AI coding agent, available as a desktop app and terminal CLI, that turns natural-language requests into file edits, code search, shell commands and git operations, decomposing complex tasks across up to 20 parallel sub-agents.

CodeCraft

CodeCraft is an autonomous coding agent, distinct from a plain chat assistant, that reads project files, searches the codebase, executes shell commands and manages git through real tool calling, switching at runtime between LLM providers such as DeepSeek, OpenAI, Anthropic, Ollama, MiMo and MiniMax behind a unified client abstraction; each agent instance can bind its own provider, model, system prompt and tool set.

A multi-agent system lets a main agent decompose a complex task and run up to 20 sub-agents, such as a code reviewer or software architect role, in parallel in the background. Agents can delegate work to each other directly through an agent-invoke tool, running the delegate in its own session with cycle detection and a depth limit to prevent infinite loops, and delegated sessions remain visible and auditable. A three-tier, human-in-the-loop safety model requires confirmation for sensitive file and path operations in manual mode and still confirms high-risk actions such as file deletion or SQL execution in automatic mode.

Built with Java. MIT licensed.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.