MCP Vetted

metaharness

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

Repository
ruvnet/metaharness
Stars
354
Last push
2026-07-03
License
MIT
Category
Developer Tools

Score breakdown — how scoring works

  • Maintenance

    30 / 30
    • Pushed within 14 days0 days ago+30

  • Adoption

    14.8 / 25
    • GitHub stars (no package published — stars weighted fully)354+14.8

  • Documentation

    20 / 25
    • Comprehensive README (6,000+ chars)24345 chars+10
    • Install / setup instructionsyes+6
    • Tools / capabilities documentedno+0
    • Code or client-config exampleyes+4

  • Trust signals

    7 / 20
    • OSS license declaredMIT+7
    • First-party vendor implementationno+0
    • DNS-verified registry namespaceno+0
    • Listed in official MCP Registryno+0
    • Owned by an organizationno+0

Install

From sourcegit clone https://github.com/ruvnet/metaharness

No package published to a registry — see the README for setup instructions.

Always review a server's code and required credentials before connecting it to your MCP client. MCP Vetted scores public metadata — it does not audit code for malicious behavior (yet). Methodology →

View on GitHub ↗