AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
metaharness
metaharness logo

metaharness

Active·★ 713·MIT·Updated 2026-10-22
★ Trending

MetaHarness is a CLI and browser Studio that mints custom AI agent harnesses from any GitHub repository, creating a repo-aware CLI, coding agent, and local MCP server tailored to the project. It acts as a factory for agent frameworks, allowing users to ship their own branded, npm-publishable AI agents with custom memory, governance, and model routing.

metaharness sits in the Multi-Agent category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Custom AI Agent Harness Generation: Mints custom AI agent harnesses from any repo, complete with a repo-aware CLI and local MCP server.. A representative use case is Creating a Repo-Specific Coding Agent: Generate a custom AI agent to assist with coding, maintenance, and automation tasks for a specific GitHub repository.. The listed license is MIT. GitHub stars are currently 711. Relevant tags include AI Agent Generation, Multi-Agent System.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#AI Agent Generation#Multi-Agent System#LLM Infra#Dev Tooling#Agent Framework Factory#Code Automation#Model Routing#Agent Governance
$ Install
$ npx metaharness my-bot --template vertical:coding --host claude-code
↗ Visit site★ GitHub
01

Features

01Custom AI Agent Harness Generation: Mints custom AI agent harnesses from any repo, complete with a repo-aware CLI and local MCP server.
02Repo Scoring & Cost Estimation: Scores any repository to assess harness fit, build likelihood, tool safety, and estimated cost per run before scaffolding.
03Model Routing & Optimization: Automatically routes requests to the cheapest model that meets quality standards, and supports training on custom data for better cost efficiency.
04Self-Evolving Harness (Darwin Mode): Enables the harness to mutate its own configuration, test changes in a sandbox, and keep only measurable improvements for continuous evolution.
05Multiple Host Compatibility: Supports deployment and execution on nine different agent hosts, including Claude Code, OpenAI Codex, pi.dev, Hermes, and GitHub Actions.
02

Why choose it

+Custom AI Agent Harness Generation: Mints custom AI agent harnesses from any repo, complete with a repo-aware CLI and local MCP server.
+Repo Scoring & Cost Estimation: Scores any repository to assess harness fit, build likelihood, tool safety, and estimated cost per run before scaffolding.
+Creating a Repo-Specific Coding Agent: Generate a custom AI agent to assist with coding, maintenance, and automation tasks for a specific GitHub repository.
+Supports 8 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Node.js
Runtime
Verified via docs
Rust
Kernel
Verified via docs
Browser
Studio UI
Verified via docs
Claude Code
Agent Host
Verified via docs
OpenAI Codex
Agent Host
Verified via docs
GitHub Actions
CI/CD
Verified via docs
05

Quick start

1
$ npx metaharness my-bot --template vertical:coding --host claude-code
06

Use cases

↳Creating a Repo-Specific Coding Agent: Generate a custom AI agent to assist with coding, maintenance, and automation tasks for a specific GitHub repository.
↳Optimizing LLM Costs in Agent Workflows: Utilize the model router to automatically select the cheapest model for each task while maintaining quality, reducing overall operational costs.
↳Continuous Improvement of Agent Performance: Employ Darwin Mode to allow agents to self-evolve and refine their configurations through sandbox testing and measurable improvements.
↳Publishing Branded Internal AI Tools: Publish custom, repo-tuned AI agents as npm packages for organizational use, ensuring consistent tooling and versioning.
↳Integrating Agents with Various LLM Platforms: Deploy the generated harnesses across multiple LLM host environments like Claude Code, OpenAI Codex, or GitHub Actions for broad compatibility.
07

Alternatives

⚡Top VS:
VSzeroshot★2.0k→VSMetaGPT★71.0k→VSAI-company★373→VSagentUniverse★2.4k→
zeroshot logo
zeroshot★ 2.0k
Your autonomous engineering team in a CLI. Point Zeroshot at an issue, walk away, and return to production-grade code. Supports Claude Code, OpenAI Codex, OpenCode, and Gemini CLI.
VSCompare→
MetaGPT logo
MetaGPT★ 71.0k
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
VSCompare→
AI-company logo
AI-company★ 373
Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.
VSCompare→
agentUniverse logo
agentUniverse★ 2.4k
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.
VSCompare→
MassGen logo
MassGen★ 1.1k
🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai
VSCompare→
cli-agent-orchestrator logo
cli-agent-orchestrator★ 1.5k
Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions
VSCompare→
thread-keeper logo
thread-keeper★ 13
Multi-agent shared brain across Claude Code/Desktop, Codex, Gemini, Copilot, VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server.
VSCompare→
chamber logo
chamber★ 12
Genesis Mind Interface — desktop chat UI for Genesis agents
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
ruvnet /
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).

713MIT
Last commit1d ago
StatusActive
CategoryMulti-Agent
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.