Log inSubmit server
Metaharness logo

Metaharness

Generate a branded, repo-aware agent harness with an npx CLI, local MCP server, memory, governance, and signed releases.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Metaharness

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "metaharness": {
      "command": "npx",
      "args": [
        "-y",
        "metaharness"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

metaharness turns a GitHub repository or blank project into a customized AI agent harness with its own CLI, local MCP server, project-scoped memory, skills, and governance policy. The browser-based Studio and `npx metaharness` workflow generate an npm-publishable ZIP without sending project data away from the machine. Use it when a repository needs a dedicated, branded agent setup rather than a general-purpose agent framework. Generated harnesses can target Claude Code, OpenAI Codex, pi.dev, Hermes, OpenClaw, RVM, or Prime Agent.

Use cases

  • Generate a repo-specific coding agent
  • Score a repository before scaffolding a harness
  • Publish a branded agent CLI for a project
  • Add scoped memory and governance to an agent workflow
  • Evaluate harness changes with bounded experiments

Key features

  • Repository-aware harness generation
  • Custom npx CLI and npm-publishable ZIP output
  • Local MCP server with project-scoped memory
  • Generated skills, slash commands, and governance policy
  • Witness-signed provenance and release gates
  • Repository scoring and model routing extensions

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2h ago via OSV.dev · metaharness (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars722Stargazers on the source repository.
Last commitTodayMost recent push to the default branch.

How Metaharness works

What metaharness does

metaharness is a factory for creating repository-specific agent harnesses. It accepts a GitHub URL or starts from a blank slate, then produces a customized package with your naming and branding, an npx <your-name> command, and the components needed to operate an agent around a project.

The generated output can include a repo-aware coding agent, recommended agents and skills, slash commands, MCP tools, project-scoped memory, governance rules, release checks, and witness-signed provenance. The result is packaged as an npm-publishable ZIP rather than used as a hosted agent service.

How it works

You can begin with the command-line interface or open the web-based Agent Harness Studio. The CLI also provides a score command for examining a repository before generation. Scoring reads the repository without running it and reports harness fit, build likelihood, tool-safety information, and an estimated cost per run.

After configuration, metaharness generates a standalone harness for a selected host. Supported host choices named by the project include Claude Code, OpenAI Codex, pi.dev, Hermes, OpenClaw, RVM, and Prime Agent. Prime Agent receives project-scoped Python-backed skills rather than MCP tools, along with an installation runbook; its generated output includes a sandbox warning when a deny-list cannot be enforced by the host.

The project also includes experimental evolution components. Darwin Mode supports bounded proposals, probes, selective composition, and metered experiment memory under caller policy. A separate autonomous variation runtime can inspect, edit, execute tools, evaluate changes, repair or revert work, branch, use structured memory, and commit while applying budgets, promotion, quarantine, rollback, and signed replay receipts.

Setup and configuration

Run the generator through the package command:

Terminal
npx metaharness

The Studio is available from the project’s GitHub Pages site. Generation can use a GitHub repository URL or a blank project. The resulting archive is intended for publication under the owner’s name and can expose a custom npx command.

Model selection is replaceable. The optional @metaharness/router package can route requests using results supplied by the user, and the project describes an optional native training dependency for that router. These routing packages are extensions to the generated harness rather than prerequisites for using the generator.

Tools and capabilities

  • Generate a branded harness from a repository or blank slate.
  • Produce a custom CLI and npm-publishable ZIP package.
  • Create project-scoped memory and governance policy.
  • Recommend agents, skills, slash commands, and MCP tools from repository structure.
  • Add release verification and witness-signed provenance.
  • Score a repository before scaffolding it.
  • Route requests among models using user-provided results.
  • Evaluate harness changes through Darwin Mode.
  • Export Prime Agent skills and an installation runbook.

Limitations and notes

Prime Agent does not provide MCP support and cannot enforce a deny-list itself. When a deny-list is present, the Prime Agent host emits a SANDBOX-REQUIRED.md notice instead of silently removing that policy.

Several advanced features are explicitly experimental. The ARC-AGI-3 packages are private and experimental, and the project makes no ARC performance claim without its stated evaluation gate. Stronger claims about autonomous variation and model-routing behavior depend on separate evaluation conditions. Treat these packages as research extensions rather than established requirements for the basic generator.

The generated harness is intended to be owned and published by the user. It is not presented as a single hosted agent or as a replacement for the model used by the harness.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Metaharness

metaharness is an MCP server that connects a generated AI agent harness to a repository or blank project and its project-scoped tools, memory, skills, and governance policy. Its main tools support repo-aware agent workflows, including generated MCP capabilities, repository scoring, and controlled harness evolution for supported hosts.

Run `npx metaharness` to start the generator. Choose a GitHub repository or blank slate, configure the harness, and use the resulting npm-publishable ZIP with a supported host. The project also provides a browser-based Agent Harness Studio for the generation workflow.

Yes. Run `npx metaharness score <repo>` to inspect a repository without executing it. The command reports harness fit, likely buildability, tool-safety information, and a rough cost per run before scaffolding.

Yes. Generated harnesses can target Claude Code and OpenAI Codex. The project also names pi.dev, Hermes, OpenClaw, RVM, and Prime Agent as supported host choices, with Prime Agent receiving generated skills rather than MCP tools.

Yes. The generated package uses the owner’s name and branding and can expose a custom `npx <your-name>` CLI. The output is an npm-publishable ZIP containing the customized harness.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMetaharness AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/metaharness?style=directory)](https://allmcps.com/mcp/metaharness)
HTML Embed
<a href="https://allmcps.com/mcp/metaharness"><img src="https://allmcps.com/api/badge/metaharness?style=directory" alt="Metaharness on AllMCPs" /></a>