Claw Code logo

Claw Code

Open-source AI coding agent in Python & Rust

CodingAI AgentsFreeOpen Source
0 Views

Open-source AI coding agent framework offering a clean-room Python and Rust rewrite of the Claude Code architecture with multi-agent orchestration.

Screenshot 1
Claw Code Overview

What is Claw Code?

Claw Code is an open-source AI coding agent framework written in Python and Rust that re-implements the Claude Code agent harness architecture from scratch.

How to use Claw Code?

Clone the GitHub repository, install Python dependencies with pip install -r requirements.txt, then run the agent via python src/main.py. Configure your preferred LLM provider and interact through slash commands or the autonomous agent loop.

Core features of Claw Code

  • Plugin-based tool system with 19 permission-gated tools
  • Autonomous terminal-native agent loop for code editing and execution
  • Multi-agent orchestration with sub-agent spawning and shared memory
  • Provider-agnostic LLM API client supporting Claude, OpenAI, and local models
  • Model Context Protocol integration across 6 transport types
  • Rust performance core with 6-crate workspace and zero-dependency JSON parser

Target audience of Claw Code

DevOps Engineers

Use cases of Claw Code

  • #1Autonomous codebase editing, refactoring, and test execution
  • #2Building customizable self-hosted AI coding infrastructure
  • #3Multi-agent task decomposition for complex engineering workflows
  • #4Claude Code alternative without subscription lock-in
  • #5Extensible foundation for custom AI agent frameworks

Claw Code Details

Claw Code is an open-source AI coding agent framework written in Python and Rust. It is a clean-room rewrite of the Claude Code agent harness architecture, created by Sigrid Jin after the March 2026 source code leak event. The codebase is composed of Rust (72.9%) for performance-critical runtime paths and Python (27.1%) for agent orchestration and LLM integration, with an active Rust migration targeting a fully native harness.

The framework ships with 19 permission-gated tools, 15 slash commands, and a multi-agent orchestration layer that can spawn sub-agents to parallelize complex tasks. It features a provider-agnostic API client supporting Claude, OpenAI, and local models, full Model Context Protocol (MCP) integration across 6 transport types, multi-layer session and memory persistence, and a three-mode permission system. Performance-critical paths are handled by a 6-crate Rust workspace with a zero-dependency JSON parser, OAuth PKCE flow, and syntax-highlighted terminal rendering.

Claw Code has accumulated over 48,000 stars and 56,000 forks on GitHub under the instructkr organization. It is freely available, auditable, and welcomes community contributions.

Claw Code Pricing

Pricing model
Free

FAQ from Claw Code

What is Claw Code?

Claw Code is an open-source AI coding agent framework built in Rust and Python. It is a clean-room rewrite of the Claude Code agent harness architecture, created by Sigrid Jin after the March 2026 source code leak.

Does Claw Code contain Anthropic's proprietary code or model weights?

No. Claw Code is a clean-room implementation written entirely from scratch. Independent audits confirm it contains no Anthropic proprietary source code, no model weights, no API keys, and no user data.

How is Claw Code different from Claude Code?

Claude Code is Anthropic's official proprietary CLI agent written in TypeScript requiring a subscription. Claw Code is open-source, written in Python and Rust, supports multiple LLM providers, and is modular and self-hostable.

What languages and technologies does Claw Code use?

The codebase is composed of Rust (72.9%) and Python (27.1%). Python handles agent orchestration, command parsing, and LLM integration, while Rust implements performance-critical runtime paths.

Who created Claw Code?

Claw Code was created by Sigrid Jin (@sigridjineth), a developer profiled by the Wall Street Journal as one of the world's most active Claude Code users. The project is maintained under the instructkr organization on GitHub.

Claw Code Website Traffic Analysis

Visit Over Time

Monthly Visits102.2K
Avg. Visit Duration00:23
Page per Visit1.75
Bounce Rate42.67%
Dec 2025 - May 2026 All Traffic

Geography

Top 5 Regions

📍China
16.38%
📍United States
7.69%
📍India
6.95%
📍Senegal
6.69%
📍Germany
5.97%
Dec 2025 - May 2026 Desktop Only

Traffic Sources

Organic Search
66.51%
Direct
16.44%
Organic Social
7.93%
Referrals
6.65%
GenAI
2.40%
Mail
0.07%
Affiliate
0.00%
Display Ads
0.00%
Paid Search
0.00%
Paid Social
0.00%
Dec 2025 - May 2026 Worldwide Desktop Only

Top Keywords

KeywordTrafficCost Per Click
claw code30.6K$ 2.51
clawcode9.2K$ 2.51
claw-code6.6K--
claw code project660--
claw code github2.3K--

Alternative of Claw Code

More Claw Code alternatives

Customer Reviews

0.00 out of 5

Based on 0 reviews

0
0
0
0
0

No published reviews yet.