RepoHQ

RepoHQ syncs all of my GitHub repositories, scores their health, and turns that into ranked, quantified next actions. An AI advisor proposes the work; a sandboxed agent factory runs it on free models and judges every change before it lands.

• 017-factor health score per repo (activity, security, deployments, docs, tests, dependencies, quality) and a single 0–100 portfolio score with weekly delta
• 02AI Advisor ranks the top 5 actions with expected score deltas, then tracks predicted vs. actual outcomes to improve itself
• 03Agent execution: advisor actions and skills are queued to a factory that writes code in a sandbox and gates every change
• 04MCP server with 14 tools exposes portfolio context and the agent lifecycle to Claude Code and other MCP clients
• 05Revenue and lifecycle tracking (MRR/ARR, Stripe sync, 8 stages from Idea to Archived) plus an opt-in public portfolio page