metaharness
View on GitHub🛠️ 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).
MetaHarness scaffolds customizable, repo-aware AI agent harnesses from a GitHub URL or blank slate. Generated harnesses can include a CLI, MCP server, project-scoped memory, skills, governance, and release verification for supported agent hosts.
Use Cases
Generate a repo-specific AI agent harnessCreate a branded, publishable agent CLIAdd project-scoped memory and skills to an agentExpose agent tools through a local MCP serverScore a repository for harness suitabilityConfigure governance policies and release verificationRoute tasks to lower-cost models
Built With
- Language
- TypeScript
- Frameworks
- MCP · Claude Code · OpenAI Codex · pi.dev · Hermes · OpenClaw · Prime Agent
Tags
agent-scaffolding · agent-harness · harness-generator · autonomous-agents · MCP · agent-memory · agent-skills · governance · model-routing · release-provenance · multi-agent · CLI