# thClaws/thClaws

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

Repository: https://github.com/thClaws/thClaws
Canonical: https://ross.abutalabs.com/products/thclaws
Homepage: https://thclaws.ai
Language: Rust
License: Apache-2.0
License Family: permissive
Topics: agent-harness, ai-agent, multi-provider, rust, tauri, claude-code, agent-teams, kms, llm-wiki, anthropic, cli, desktop-app, developer-tools, gemini, llm, mcp, model-context-protocol, ollama, openai, telegram-bot
Last push: 2026-08-25T16:40:43+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 9
- inputs: {"age_days": 136, "days_push": 8, "days_rel": 8, "gap_med": 0, "n_releases_24m": 168}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1208, forks 171 (observed 2026-08-28T04:03:59.678756+00:00)

## What it is
thClaws is an open-source AI agent harness written in native Rust that ships as a single binary offering a desktop GUI, CLI, headless, and webapp interface. It supports multiple LLM providers (Anthropic, OpenAI, Gemini, Ollama, OpenRouter), MCP integration, skills, plugins, agent teams, and built-in media generation tools, all running locally on the user's machine.

## Use cases
- run an AI coding agent locally on my machine
- open-source alternative to claude code
- chat with multiple LLM providers from one app
- use MCP tools with a desktop AI agent
- generate images and video with AI from a desktop app
- run AI agent teams that coordinate on tasks
- headless AI agent automation from the terminal
- self-hosted agent that keeps my data local

## When to choose
- you want a local-first, single-binary agent harness with GUI and CLI from one codebase
- you need multi-provider LLM support without cloud lock-in
- you want MCP, skills, plugins, and agent-team coordination built in
- you prefer native Rust performance over Electron-based agent tools

## When to avoid
- you need a mature, battle-tested product with a large ecosystem
- you only want a lightweight library to embed in your own app rather than a full application
- you require cloud-managed agent orchestration at scale
- you need official support or SLAs for enterprise use

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, mcp, chatbot, cli, gui, prompt-engineering, developer-tools, image-processing, video-processing
- domain: large-language-models, developer-tools, self-hosted, cross-platform
- platform: windows, cli, cross-platform, rust
- tags: agent-harness, multi-provider, mcp-client, tauri, agent-teams, local-first, media-generation, openrouter, telegram-bot, skills, plugins, ai-agents, command-line, automation, macos, linux, desktop

## Member repositories
- thClaws/thClaws (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:59.678756+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:18:56.486348+00:00, confidence not recorded.
  - readme: https://github.com/thClaws/thClaws (fetched 2026-08-28T04:03:59.678756+00:00, sha 9367c5763685)
  - homepage: https://thclaws.ai (fetched 2026-08-29T12:26:33.921208+00:00, sha f84b8470f32d)
- Data as of 2026-08-30T08:39:29.467469+00:00.
