revfactory/harness
harness
A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
Usage guide
harness is an open-source project around claude-code, claude-code-plugin, harness-engineering with 7,900 GitHub stars. This guide focuses on when to use it, how to install it, how to run the first example, and what to verify before adopting it.
Key features
- Implemented mainly in HTML, useful for judging integration effort in a similar stack.
- GitHub detected the Apache-2.0 repository license, which generally permits commercial use. This signal only covers the repository license; review its obligations and any model weights, datasets, dependencies, or external services before commercial adoption.
- The project has a homepage, so cross-check docs, examples, and release information beyond GitHub.
Best for
- Evaluating harness for HTML AI workflows.
- Comparing a GitHub project with 7,900 stars and current repository activity.
Pros
- harness has visible GitHub traction with 7,900 stars. Topics: claude-code, claude-code-plugin, harness.
- The project provides an external homepage for deeper evaluation.
Cons
- Production fit still depends on documentation depth, issue activity, and release cadence.
- License review should confirm the Apache-2.0 terms fit your use case.
Production readiness
harness should be validated with its README, release history, open issues, and integration requirements before production use.
License risk
Apache-2.0 is reported by GitHub; review the repository license before redistribution or commercial use.
harness architecture preview
harness's main path starts at the entry surface, runs through Coding agent runtime, combines Claude, Runtime context, GitHub, and returns Assistant response / action result.
Entry
Web / product entry
Users start from a web UI, hosted product surface, or browser-based workflow.
https://revfactory.github.io/harness/
Runtime
Coding agent runtime
The runtime reads developer intent, inspects repository context, plans edits, and returns code-oriented actions.
coding workflow
Model
Claude
Model calls are likely routed through Claude based on README and topic signals.
Claude
Context
Runtime context
Runtime state, user input, repository files, or configuration provide context for each task.
context signal
Tools
GitHub
Tool adapters let the runtime act outside the model through GitHub.
GitHub
Output
Assistant response / action result
The final result is a response, action, or task completion returned through the active channel.
assistant output
Featured video
dory frida parrots
How to put a parrot harness. Check this video - African Grey
5,710,756 views ยท 2021-06-20
Install tutorial
Before you install
- A clean working directory for the first test run
Check the runtime environment
Confirm your system can run a HTML project before starting the installation steps.
Get the project files
Start from the official repository or package so the first run matches the documented behavior.
$ git clone https://github.com/revfactory/harness.gitInstall or build dependencies
No extra setup command was detected. Check the README before adding custom configuration.
Adoption guidance and sources
Practical use cases
Agent workflow prototype
Use it to validate task decomposition, tool calling, memory, tool permissions, and result review loops.
A meta-skill that designs domain-specific agent teams, defines special
This is one of the documented reasons to evaluate harness before choosing a stack.
Focus area: claude-code
This is one of the documented reasons to evaluate harness before choosing a stack.
AI Agents project comparison
Compare harness with similar projects before committing to a stack.
Before adopting
- Complete one clean-environment verification using the official harness setup path.
- Review repository license, model weights, external services, and dependency terms for your use case.
- Check recent commits, release cadence, issue response, and documentation depth.
- Evaluate output quality, latency, resource usage, and recovery behavior with a small dataset.
Configuration notes
- Review README configuration notes before using production data.
Sources checked
These links are used to verify repository, documentation, or tutorial details. Review the source pages before adopting the project.
Troubleshooting
- If installation fails, first confirm the command is being run from the README-specified directory.
- If dependencies conflict, retry in a fresh virtual environment, container, or working directory.
- If output looks wrong, return to the smallest documented harness example before adding complex data.
- For keys, model files, or external services, verify environment variables, local paths, and permissions one by one.
- Before production use, review recent updates, open issues, license terms, and safety boundaries.
What is harness?
harness is an open-source ai agents project. A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
How do I install harness?
Start with the official README. The first detected setup step is: git clone https://github.com/revfactory/harness.git.
Is harness beginner-friendly?
If you already know the HTML ecosystem, start with the smallest example. Otherwise test it in an isolated environment first.
Can harness be used commercially?
GitHub detected the Apache-2.0 repository license, which generally permits commercial use. This signal only covers the repository license; review its obligations and any model weights, datasets, dependencies, or external services before commercial adoption.
Does harness need a GPU?
GPU requirements depend on the workload, model, and dataset size. Start with the smallest README example before scaling up.
How should I decide whether to adopt harness?
Evaluate setup cost, maintenance activity, issue health, license terms, and fit with your real workflow.