thClaws  by thClaws

AI agent workspace for local automation and coordination

Created 1 week ago

New!

545 stars

Top 58.3% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

thClaws is an open-source, native Rust AI agent harness platform enabling local execution for enhanced user sovereignty. It empowers knowledge workers and engineers by allowing AI agents to code, automate, search knowledge bases, and coordinate operations directly on their machine, minimizing cloud dependency.

How It Works

This platform delivers a unified, native Rust binary with Desktop GUI, CLI REPL, and non-interactive modes. It supports numerous AI providers (OpenAI, Anthropic, Gemini, local Ollama) and auto-detects models. thClaws champions open standards like AGENTS.md and SKILL.md for workflow packaging and interoperability, ensuring portability across agent tooling ecosystems. Its architecture includes a plugin system for custom skills, commands, and Model Context Protocol (MCP) servers.

Quick Start & Requirements

Pre-built binaries are available for macOS, Windows, and Linux via thclaws.ai/downloads. Source builds require Rust 1.85+, Node.js 20+, and pnpm 9+. API keys use OS keychain or .env. Documentation is accessible via thclaws.ai and an upcoming manual.

Highlighted Details

  • Multi-Provider: Seamlessly switch between numerous AI providers and models.
  • Open Standards: Adheres to AGENTS.md, SKILL.md, and MCP for interoperability.
  • Extensible: Supports custom Skills, MCP servers, and bundled Plugins.
  • Local Knowledge: Features persistent memory and Knowledge Bases (KMS) searchable via grep/read.
  • Orchestration: Enables delegation to sub-agents and coordination via Agent Teams.
  • Safety: Includes filesystem sandboxing, destructive command flagging, and user approval.
  • Offline & Scripting: Fully offline capable with local models (Ollama); supports shell escape (!).

Maintenance & Community

Developed by ThaiGPT Co., Ltd. The README does not specify community channels or a public roadmap.

Licensing & Compatibility

Dual-licensed under MIT or Apache 2.0, permitting commercial use and integration into closed-source projects. Enterprise features, hosting, and support are commercial offerings.

Limitations & Caveats

The full user manual is noted as "upcoming." Enterprise features, hosting, and support are commercial products, suggesting potential differences in feature sets or support levels compared to the FOSS client.

Health Check
Last Commit

13 hours ago

Responsiveness

Inactive

Pull Requests (30d)
21
Issues (30d)
16
Star History
550 stars in the last 8 days

Explore Similar Projects

Starred by Gagan Bansal Gagan Bansal(Coauthor of AutoGen; Research Scientist at Microsoft Research), Elvis Saravia Elvis Saravia(Founder of DAIR.AI), and
1 more.

agent-framework by microsoft

2.2%
10k
AI agent and multi-agent workflow framework
Created 1 year ago
Updated 5 hours ago
Starred by Elie Bursztein Elie Bursztein(Cybersecurity Lead at Google DeepMind), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
7 more.

SuperAGI by TransformerOptimus

0.1%
17k
Open-source framework for autonomous AI agent development
Created 3 years ago
Updated 1 year ago
Starred by Wes McKinney Wes McKinney(Author of Pandas), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
22 more.

autogen by microsoft

0.4%
57k
Agentic framework for multi-agent AI applications
Created 2 years ago
Updated 1 week ago
Feedback? Help us improve.