RepoRadar
Leave a Tip
Item detail

ruvnet/agent-harness-generator

Agent Harness Generator is a MIT-licensed meta-harness for AI agents that scaffolds a focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. It works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and an RVM hardware-isolated sandbox, so teams can ship a self-contained agent product instead of a pile of skills.

Open source →Back to radar
Score8.0
Popularity72.0
Riskconditional
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum7.0
Maturity7.8
Open-source/build8.4
Evidence7.2
Workflow potential9.5
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for agent teams that want a reproducible starting point for a new product: install the CLI, run metaharness <name>, review the scaffolded MCP server and memory layer, and verify the witness-signed release flow on a non-sensitive workload before extending it to real customer data or production credentials.

Who should use it

agent product teamsinternal developer platform ownersMCP early adoptersstartup founders shipping agent products

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

witness-signed releases need a clear key custody story before the pattern is used in production; scaffolded MCP servers can become shared-credential targets; review access controls before exposing them.

Evidence links

Closest alternatives / related signals

agent-harnessscaffoldingmcpwitness-signingruvnetmeta-harness