Hadron 发布原生桌面多模型 LLM 集群工作区

The Native Desktop Workspace for Multi-Provider LLM Swarms

Orchestrate Claude, Antigravity, OpenAI, Ollama, and CLI Agents in One Workspace

⚡ What is Hadron?

Hadron is a native, GPU-accelerated desktop workspace built in Rust for orchestrated multi-provider LLM swarms. It brings models from Anthropic (Claude), Google Antigravity, OpenAI, Ollama, OpenRouter, and custom coding CLIs into a unified room where agents collaborate, exchange context, and delegate tasks using @mentions.

Behind the interface, agents (called Quarks) execute concurrently over a zero-CPU filesystem event bus (field.jsonl), work safely in isolated git worktrees, and submit code changes through an automated Merge Gate that runs tests before landing anything on main.

💡 Key Superpowers

• 💬 Collaborative Multi-LLM Chat: Mix models in a single thread — @claude, @ollama, @agy, @openai, and many more see each other's output, share context, and execute parallel sub-tasks via Hub-and-Spoke orchestration.
• 🛡️ Git Worktrees & Automated Merge Gate: Agents work in isolated git worktree branches. The Merge Gate automatically rebases onto main and runs your test suite before clean code lands.
• ⚡ Native GPUI Desktop App: Lightning-fast GPU-accelerated UI with multi-tab PTY terminals, interactive git commit graph, live plan tracking, interactive 3D cosmic swarm visualizer, native interactive Mermaid diagram rendering, robust color emoji font fallbacks, and real-time multi-protocol token telemetry.
• 🛠️ Hadron Forge & Developer Power Tools: 50+ built-in MCP developer capabilities — AST precision edits via blake3, isolated PTY terminals, headless browser testing, LSP code intelligence, background process supervision, automated git bisect, and flamegraph profiling. Detailed in Power Tools Suite.
• 🧠 Persistent Nucleus Memory & Universal Absorption: Cross-session shared memory within a configurable budget (16/32/64/128 KiB), plus /absorb to seamlessly import memories, invariants, skills, and plans from .agents/, .claude/, .cursor/, .windsurf/, .kimi/, .superpowers/, and many more.
• 🤖 Autonomous Headless Swarm Runner: Standalone non-interactive CLI runner (hadron run / hadron ci) for CI/CD automation, speculative shadow pre-testing, AST-aware rebase healing, and tiled multi-PTY terminals.
• 🎯 Autonomous Swarm Control: Built-in slash commands (/goal, /loop, /absorb, /release, /git-init, /resume, /clear, /home, /canvas, /intercom, /dream, /timelapse, /radar, /baseline, /preview-rebase, /steer, /scout) and 25 bundled workflow & engineering skills (TDD, security review, architecture audit, systematic debugging, design specs).

🚀 Quick Start

Prerequisites

• Rust: Toolchain (edition 2021, Rust 1.93+ required).
• OS: Linux (X11/Wayland), macOS, or Windows (native MSVC or WSL2).
• LLM Access: Any ACP agent (e.g. Claude Code), Antigravity, local Ollama, or API key for OpenAI / OpenRouter / Anthropic.

1. Install Hadron

# Install the full binary suite (--locked is mandatory)
cargo install --locked --git https://github.com/s0lda/hadron.git hadron

2. Launch in Any Repo

# Open or create a swarm workspace in your project directory
cd ~/dev/my_project && hadron

# Or execute headlessly in CI / terminal batch mode
hadron run "Implement user authentication with tests"
hadron ci --plan .hadron/docs/plans/<plan_name>

📚 Documentation & Deep Dives

Explore Hadron's mechanics, architecture, and developer guides in the /docs directory:

🔌 Provider & Model Ecosystem

Hadron connects an expanding ecosystem of AI agents, local models, cloud APIs, and terminal tools into a single orchestrated workspace. Any binary, endpoint, or script matching supported protocol interfaces can be seated directly into your swarm:

• 🤖 ACP (Agent Client Protocol): Resident agent processes with automatic session resumption, model selection, and tool execution.
• 🌉 Custom SDK Bridges: Embedded adapters for SDK-based agent runtimes (such as Google Antigravity).
• ☁️ Local & Cloud HTTP Endpoints: Zero-config connection to local model servers (Ollama, LM Studio) and cloud model aggregators or APIs (OpenAI, OpenRouter with 400+ models, or any OpenAI-compatible endpoint).
• 💻 CLI & PTY Transports: Stdio wrappers (CliSpec) for terminal scripts and interactive PTY terminal seats alongside LLM agents in the chat room.

⌨️ Essential Keyboard Shortcuts

📄 License & Community

• License: Apache License 2.0
• Contributing: CONTRIBUTING.md
• Security: SECURITY.md
• Code of Conduct: CODE_OF_CONDUCT.md
• Glossary: Physics Metaphor & Vocabulary
• Commands: Chat Commands Reference