The open-source software and hardware platform for domain-specific harnesses. Run Claude Code, Codex and every coding agent across your machines, make them specialists in CAD, PCBs, robotics and games, and keep them on your desk with the open-hardware Harness device.
# Add to your Claude Code skills
git clone https://github.com/autonomous-ai/openharnessLast scanned: 9/20/2026
{
"issues": [
{
"file": "README.md",
"line": 145,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://harness.autonomous.ai/cli/install.sh | bash\"",
"severity": "low"
}
],
"status": "PASSED",
"scannedAt": "2026-09-20T09:06:21.256Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how openharness compares with popular alternatives.
openharness is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by autonomous-ai. The open-source software and hardware platform for domain-specific harnesses. Run Claude Code, Codex and every coding agent across your machines, make them specialists in CAD, PCBs, robotics and games, and keep them on your desk with the open-hardware Harness device. It has 486 GitHub stars.
Yes. openharness passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/autonomous-ai/openharness" and add it to your Claude Code skills directory (see the Installation section above).
openharness is primarily written in C. It is open-source under autonomous-ai on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh openharness against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
An open-source workshop for technical founders who build across disciplines.
Use Claude Code, Codex, and other coding agents to build software, design parts and circuit boards, explore data, and make videos. OpenHarness brings your agents, domain tools, and live viewers into one workspace, with persistent agent sessions across your machines.
Use the desktop app on its own, or add the optional open-hardware Harness device to follow your agents, answer their questions, and speak new tasks from your desk.
Who it's for · What you can make · Run it · Harness device · Architecture · Contribute
The ideal user is a technical founder who is also a polymath: someone with an engineering or coding background whose curiosity and responsibilities span product, design, analysis, and marketing. You already know how to build with code. Harness brings that way of working to CAD, circuit boards, games, videos, and documents, with agents and tools for each craft.
You might prototype a feature, explore customer data, design an enclosure, and make a launch video. Give each job an agent with the right tools, inspect what it makes, and steer the next iteration. The code and project files are there to read, change, version, and build on.
From handoff to hands-on. You bring intent and judgment; your agents write and run code. Each harness supplies the tools and feedback for a different craft. You can get your hands on more of the product and the work of bringing it to customers.
Engineers, makers, and creators who share that approach are welcome too. The ideal-user guide records who we're building for and how the app, community, and device serve them.
Coding agents can build far more than software. Code is the common medium: geometry scripts make parts, animation code makes videos, and analysis code turns data into charts and findings. A harness gives the agent the tools and feedback to work in that domain.
A domain-specific harness turns a coding agent into a specialist. It brings the domain's instructions and skills, a pinned toolchain, a project template, a verdict the app can read, and a live viewer for what the agent makes. You chat on one side; the board, the part, the robot or the game takes shape on the other, and stays interactive after the agent is done.
A DSH is a folder with a harness.json. The agent does the reasoning; the harness brings the tools
and the view. Adding a domain never needs a change to the app or the daemon.
| Domain | Harnesses |
|---|---|
| CAD | Autonomous Workshop, text-to-cad |
| 3D | Blender |
| Electronics | Autonomous Circuit, CircuitJS, Yosys |
| Games | Godogen, Phaser |
| Documents and diagrams | Marp, Typst, Excalidraw |
| Video and music | OpenMontage, Remotion, Manim, Strudel |
| Simulation and analysis | MuJoCo, RDKit, marimo |
Each one wraps an open-source project under its own name, credits it, pins its toolchain, and installs on a fresh machine from the Harness Store. Eight shared viewers (CAD, 3D models, documents, games, film, video, MuJoCo, web) mean a new harness rarely needs to write its own.
The harness we'd love to see next is the one for the tool you use. KiCad, FreeCAD, OpenSCAD, Godot, Jupyter, QGIS, Home Assistant, LilyPond, Inkscape — or your own company's toolchain. A harness can live in this repository or in yours.
Every picture is real output from the harness's own toolchain, and the prompt is the one that made it.
Keep the agents doing that work together, wherever they run.
~/.claude, ~/.codex and
so on. See the engine list.On another machine:
curl -fsSL https://harness.autonomous.ai/cli/install.sh | bash
harness login
harness start
Then Machines → Link Machine in the app.
macOS is the primary tested platform. Linux builds exist and feature parity is in progress; Windows is work in progress. Embedded live viewers require macOS; remote viewers also need a current Harness CLI on both machines. The app and daemon still need a Harness account to start; account-free local use is tracked.
For macOS, install Node.js 20+, tmux, Xcode, and Flutter 3.47+ / Dart 3.13+:
git clone https://github.com/autonomous-ai/openharness.git
cd openharness
(cd cli && npm ci)
make install-cli
cd desktop
flutter config --enable-swift-package-manager
flutter pub get
flutter run -d macos
make install-cli installs this checkout's CLI and restarts the local daemon. The
development guide covers tests and isolated environments.
flowchart LR
device["Harness device"] -- USB --> daemon
app["Harness app<br/>(Flutter)"] -- loopback --> daemon["harness daemon<br/>(TypeScript)"]
daemon --> tmux["tmux"] --> agents["Claude Code · Codex · OpenCode · …"]
daemon --> dsh["DSH toolchain<br/>+ live viewer"]
daemon <-- "E2EE · WebRTC" --> relay["Harness relay"]
relay <--> remote["daemons on your<br/>other machines"]
The [architecture guide](docs/archi