#771 · Primary category: AI Agents & Automation

metaharness

agent-harness agent-harness-generator agent-scaffolding agentic-ai agentic-framework autonomous-agents claude-code codex create-agent-harness hermes-agent mcp mcp-server multi-agent openai-codex openclaw pi-dev rvm sandboxing scaffold scaffolding

🛠️ 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).

Project last updated:08/30/26

GitHub Stars

623

Forks

74

Contributors

5

License

MIT

Why we included this project

MetaHarness is a factory for agent harnesses rather than another agent runtime. Point it at a GitHub URL or a blank slate and it generates a branded, npm-publishable harness for that repo, complete with a repo-aware CLI, a local MCP server, project-scoped memory, skills built from the actual file layout, and a governance policy. The result runs inside Claude Code, Codex, pi.dev, Hermes, OpenClaw, or RVM, whichever host you already use. That makes it a good fit for teams that want a coding agent tailored to their own codebase, minted in under a minute and published under their own npx command. It also includes extras like a repo scoring report card, a model router, and a self-improvement mode that tweaks the harness config and keeps only the changes that measurably help.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category