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).
- 713 estrellas
- 88 forks
- 180 issues abiertos
- Lenguaje: TypeScript
- Licencia: MIT
- actualizado
Instalación
git clone https://github.com/ruvnet/metaharness && cp metaharness/*.md ~/.claude/agents/- Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
- Start a new Claude Code session to load the agents.
- Delegate work to them with the Task/Agent tool or by name.
18 items en este repositorio
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a vertical AI assistant for X".
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable `npm install @metaharness/kernel@X.Y.Z` next step. Exits 2 if no .harness/manifest.json at path.
Health-check the harness: kernel load, MCP wiring, memory backend, host adapter.
Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/* example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming, repo-maintainer).
GCP Secret Manager integration: validate setup, fetch values, or confirm an NPM_TOKEN is non-revoked via `npm whoami`. Used for publish-time token rotation without long-lived keys in CI.
List the available harness templates and what each one ships with. Use when the user asks "what templates are available", "what verticals does the harness generator support", or "show me what I can scaffold".
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
Turn a feature request into a minimal, file-level implementation plan before any code.
Publish a generated harness to npm — runs the smoke test, signs the witness manifest, and dispatches `npm publish --provenance` from your tagged release.
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.
Review the current working diff for correctness, security, and reuse.
5-dimension scorecard (0-100, grade A/B/C/F) for a scaffolded harness. Dimensions: Repo understanding (25%), Agent usefulness (25%), MCP safety (20%), Test coverage (15%), Publish readiness (15%). Emits a 6-field badges block (score + mcpRisk + 4 booleans) ready for the harness README. Exit 0 A/B, 1 C, 2 F.
MCP threat-model artifact for a scaffolded harness. Reports allowed/denied tools, dangerous permissions count, secrets reachability, network/shell/file-write grants, default-deny posture. Verdict: clean (exit 0) / medium (exit 1) / high (exit 2). The 'enterprise gold' artifact for PR + compliance review.
Drift detection + apply for a scaffolded harness. Re-renders the template with the same vars, computes added/removed/changed file plan, and applies with Git-style conflict markers or .rej files. Default is dry-run.
Release-readiness umbrella check for a scaffolded harness — runs doctor, witness verify, hardcoded-path scan, MCP server config, and GCP Secret Manager validation in one shot. Exits non-zero if any sub-check fails.
Verify the Ed25519 witness manifest of a scaffolded harness. Fast yes/no signature check that proves the publisher signed this exact file set — separate from the full release-readiness umbrella in validate-harness.
Resumen de Subagents
Lo que la gente pregunta sobre metaharness
¿Qué es ruvnet/metaharness?
ruvnet/metaharness es subagents para el ecosistema de Claude AI. 🛠️ 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). Tiene 713 estrellas en GitHub y su última actualización registrada es del 2026-10-23.
¿Cómo se instala metaharness?
Puedes instalar metaharness clonando el repositorio (https://github.com/ruvnet/metaharness) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar ruvnet/metaharness?
Nuestro agente de seguridad ha analizado ruvnet/metaharness y le ha asignado un Trust Score de 97/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene ruvnet/metaharness?
ruvnet/metaharness es mantenido por ruvnet. La última actividad registrada en GitHub es del 2026-10-23, con 180 issues abiertos.
¿Hay alternativas a metaharness?
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.