The open source software factory for expert engineers

AI coding agents are powerful but unpredictable. You either babysit every step or review a 50-file diff you don't trust. Arc gives you a middle path: define the process as a graph, let agents execute it, and intervene only where it matters.

---

Key Features

• 🔀 Deterministic workflow graphs -- Define pipelines in Graphviz DOT with branching, loops, parallelism, and human gates. Diffable, reviewable, version-controlled.
• 🙋 Human-in-the-loop -- Approval gates pause for human decisions. Steer running agents mid-turn. Interview steps collect structured input. You stay in control without babysitting.
• 🎨 Multi-model routing -- Route each node to the right model and provider with CSS-like stylesheets. Cheap models for boilerplate, frontier models for hard reasoning, with automatic provider fallback.
• ☁️ Cloud sandboxes -- Run agents in isolated Daytona cloud VMs with snapshot-based setup, network controls, and automatic cleanup.
• 🔌 SSH access and preview links -- Shell into running sandboxes with arc ssh and expose ports with arc preview for live debugging while workflows run.
• 🌲 Git checkpointing -- Every stage commits code changes and execution metadata to Git branches. Inspect diffs, revert mistakes, resume interrupted runs, or trace exactly how and why each change was made.
• 📊 Automatic retros -- Each run generates a retrospective with cost, duration, files touched, and an LLM-written narrative rating smoothness and flagging friction points.
• ⚡ Comprehensive API -- arc serve exposes a full REST API with SSE event streaming and a React web UI. Run workflows programmatically, build integrations, or operate Arc as a service.
• 🦀 Single binary, no runtime -- One compiled Rust executable with zero dependencies. No Python, no Node, no Docker required to get started.
• ⚖️ Open source (MIT) -- Full source code, no vendor lock-in. Self-host, fork, or extend to fit your workflow.

Read the full documentation for details.

---

Quick Start

Install

Download the latest release for your platform:

# macOS (Apple Silicon)
curl -fsSL https://github.com/brynary/arc/releases/latest/download/arc-aarch64-apple-darwin.tar.gz | tar xz
sudo mv arc /usr/local/bin/

# Linux (x86_64)
curl -fsSL https://github.com/brynary/arc/releases/latest/download/arc-x86_64-unknown-linux-gnu.tar.gz | tar xz
sudo mv arc /usr/local/bin/

Or download directly from GitHub Releases.

Build from source

Requires Rust (latest stable):

git clone https://github.com/brynary/arc.git
cd arc
cargo build --release
# Binary is at ./target/release/arc

Run the setup wizard

arc install

Initialize your project

cd my-repo/
arc init

Run your first workflow

arc run hello

---

Example Workflow

A plan-approve-implement workflow where a human reviews the plan before the agent writes code:

digraph PlanImplement {
    graph [
        goal="Plan, approve, implement, and simplify a change"
        model_stylesheet="
            *        { llm_model: claude-haiku-4-5; reasoning_effort: low; }
            .coding  { llm_model: claude-sonnet-4-5; reasoning_effort: high; }
        "
    ]

    start [shape=Mdiamond, label="Start"]
    exit  [shape=Msquare, label="Exit"]

    plan      [label="Plan", prompt="Analyze the goal and codebase. Write a step-by-step plan.", reasoning_effort="high"]
    approve   [shape=hexagon, label="Approve Plan"]
    implement [label="Implement", class="coding", prompt="Read plan.md and implement every step."]
    simplify  [label="Simplify", class="coding", prompt="Review the changes for clarity and correctness."]

    start -> plan -> approve
    approve -> implement [label="[A] Approve"]
    approve -> plan      [label="[R] Revise"]
    implement -> simplify -> exit
}

Agents run as multi-turn LLM sessions with tool access. Human gates (hexagon) pause for approval. The stylesheet routes planning to a cheap model and coding to a frontier model. See the DOT language reference for the full syntax.

---

Help or Feedback

• Read the documentation
• Bug reports via GitHub Issues
• Feature requests via GitHub Issues
• Email bryan@qlty.sh for questions

---

Contributing

See CONTRIBUTING.md for build instructions and development workflow.

---

License

Arc is licensed under the MIT License.