agent-harness-generator
Reduces time-to-deployment for specialized AI agents by auto-generating production-ready harnesses with CLI, memory, and release infrastructure, eliminating …
MetaHarness (renamed from agent-harness-generator) mints a custom AI agent harness from any GitHub repo or a blank slate: a repo-aware CLI and coding agent, a local MCP server, scoped memory, generated skills, governance policy, and witness-signed releases. Run npx metaharness or use the browser Studio; output drops into Claude Code, OpenAI Codex, pi.dev, Hermes, OpenClaw, or RVM and ships as an npm-publishable package under your own name.
- Generate a custom AI agent with built-in CLI and MCP server capabilities for your team's specific workflows.
- Create a branded agent harness with persistent memory and learning loops to improve performance over time.
- Scaffold a production-ready agent framework with witness-signed releases for compliance and audit tracking.
Reduces time-to-deployment for specialized AI agents by auto-generating production-ready harnesses with CLI, memory, and release infrastructure, eliminating boilerplate and standardizing agent architecture across teams.
Platform engineering teams building internal AI agent ecosystems or multi-agent deployment infrastructure.
https://github.com/ruvnet/metaharness
By ruvnet
How to Get It
npx metaharness
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me generate a custom AI agent with built-in CLI and MCP server capabilities for my team's specific workflows
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 135 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 135 GitHub stars; contributors unknown; last commit 0d ago; license MIT.