metaharness — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ruvnet · MCP Server · ★ 595

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is metaharness safe to install? View the security audit →

About metaharness

MetaHarness Mint a custom AI agent harness from any repo. · open the Studio → (Repo: · CLI: · Library: ) What this is Every serious repo deserves its own agent. A repo-aware CLI, a repo-aware coding agent, a local MCP server, memory scoped to the project, skills generated from the actual file layout, governance policy, release verification, witness-signed provenance. mints those, on demand, from a GitHub URL or a blank slate. It is not another agent framework. It is a factory for agent

agent-harnessagent-harness-generatoragent-scaffoldingagentic-aiagentic-frameworkautonomous-agentsclaude-codecodexcreate-agent-harnesshermes-agent

Quick Facts

Stars595
Forks72
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score65.3474134312773/100
Open Issues38
Last Updated2026-08-18
Created2026-06-13
Platformsclaude-code, cli, codex, mcp, node
Est. Tokens~20k

Compatible Skills

These tools work well together with metaharness for enhanced workflows:

  • Zleap-Agent — semantic(0.43)+complementary+same_lang+similar_pop+shared_platform (65%)
  • Chorus — semantic(0.43)+complementary+same_lang+similar_pop+shared_platform (65%)
  • munder-difflin — semantic(0.42)+complementary+same_lang+similar_pop+shared_platform (65%)
  • openrig — semantic(0.40)+complementary+same_lang+similar_pop+shared_platform (64%)

metaharness alternative? Top 6 similar tools

Looking for a metaharness alternative? If you're comparing metaharness with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • turbo-flow by marcuspat · ⭐ 168

    Advanced Agentic Development Environment for DevPods, GitHub Codespaces, Rackspace Spot & more. Ruflo orchestr

  • commonly by Team-Commonly · ⭐ 1.3k

    Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and works

  • memorix by AVIDS2 · ⭐ 662

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • bitrouter by bitrouter · ⭐ 220

    The context-aware model router that learns & adapts to your agent workflows. Lightweight & extensible, works w

  • SWE-AF by Agent-Field · ⭐ 972

    Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a

  • codexia by milisp · ⭐ 889

    Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is metaharness?

metaharness is 🛠️ 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, Code. It is categorized as a MCP Server with 595 GitHub stars.

What programming language is metaharness written in?

metaharness is primarily written in TypeScript. It covers topics such as agent-harness, agent-harness-generator, agent-scaffolding.

How do I install or use metaharness?

You can find installation instructions and usage details in the metaharness GitHub repository at github.com/ruvnet/metaharness. The project has 595 stars and 72 forks, indicating an active community.

What license does metaharness use?

metaharness is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to metaharness?

The top alternatives to metaharness on Agent Skills Hub include turbo-flow, commonly, memorix. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse MCP Server tools