Back to directory

Clawd-Code

Clawd-Code is a production-oriented Python reimplementation of Claude Code, ported from its real TypeScript architecture into a working CLI agent with a tool-calling loop, streaming REPL and session history.

Clawd-Code

Clawd-Code rebuilds Claude Code's architecture in Python rather than shipping a source dump, keeping the original design while adapting it to idiomatic Python. It implements a real agent runtime with a tool-calling loop, a streaming REPL, session history and multi-turn execution, token streaming combined with a tool-aware agent loop, a programmable skill runtime with tool sandboxing, and instant web fetch for pulling in external context.

It is intended to be readable and hackable, with a test suite and markdown-driven skills for extending its behavior, and is under active development with new features shipped weekly.

It is written in Python and licensed under MIT.

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.