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.

What it solves

thClaws is a native-Rust AI agent workspace designed for local execution. It provides a sovereign environment where users can run multiple specialized AI agents (for coding, research, or writing) side-by-side in a single project, ensuring each agent remains self-contained with its own memory, settings, and browser profiles.

How it works

The project operates as a single binary that supports four different user interfaces: a Desktop GUI, a CLI REPL, a non-interactive mode for scripts, and a Webapp. It uses a unified agent loop and tool registry to manage interactions. To ensure security, it implements OS-level Bash confinement (using macOS Seatbelt, Linux Landlock, or bubblewrap) to prevent agents from accessing files outside the workspace.

Who it’s for

It is built for developers and power users who want an open-source, local-first AI agent harness that can automate tasks, manage knowledge bases, and coordinate multiple agents without relying on a cloud-only ecosystem.

Highlights

  • Multi-Agent Workspaces: Run up to 8 agents simultaneously, each with its own isolated process and session.
  • Extensive Provider Support: Integrates with over 1,100 models across 27 providers, including local options via Ollama.
  • Media Studio: Built-in tools for text-to-image, image editing, and text/image-to-video generation.
  • Open Standards: Supports the Model Context Protocol (MCP) for tools and AGENTS.md for project instructions.
  • Coded in Rust: High-performance native binary with a focus on security and sovereignty.
  • Advanced Orchestration: Features include a "Plan mode" for step-by-step approval, recurring job scheduling, and long-running goal-oriented loops.

Related

  • Project
    microclaw/microclaw

    MicroClaw is a self‑hosted Rust platform for AI agents that can run as a server, a native desktop “Work” app, or be embedded via an SDK. It offers multi‑step tool use, durable sessions, SQLite‑based memory, many chat channel adapters, and built‑in safety guardrails, all share‑able across its three product surfaces.

  • Project
    qhkm/zeptoclaw

    A fast, secure, and local-first personal AI assistant infrastructure written in Rust, providing sandboxed autonomy and multi-provider LLM support in a single 6MB binary.

  • Project
    zeroclaw-labs/zeroclaw

    A self-hosted agent runtime written in Rust that connects LLM providers to multiple communication channels and hardware tools while ensuring user ownership of data and infrastructure.

  • Project
    ultraworkers/claw-code

    Claw Code is a Rust‑based CLI harness (`claw`) for running autonomous LLM agents. It supports Anthropic, OpenAI, and local providers, offers health checks, interactive and one‑off prompting, and includes extensive docs for building, configuring, and testing. Build from source (or install the upstream `agent-code` binary) and use it to manage agent‑driven workflows.

  • Project
    ValueCell-ai/ClawX

    ClawX is a desktop interface for OpenClaw AI agents that provides a graphical, no-terminal experience for managing AI workflows, scheduled tasks, and local computer automation.