i built
for those of you who are autoresearch pilled , or have been meaning to get into autoresearch but dont know how. Its an opensource Claude Code & Codex plugin that optimizes code through experiments
you hand it a codebase. it finds a benchmark, runs the baseline, then fires off parallel agents to try to beat it. kept if better, discarded if worse.
inspired by karpathy's autoresearch, but with structure on top:
- tree search over greedy hill-climb β multiple forks from any committed node
- N parallel agents in git worktrees
- shared failure traces so agents don't repeat each other's mistakes
- regression gates
under the hood: each experiment is a git worktree branching from its parent. commits on score improvement + gate pass. discards + worktree cleanup on regression. everything observable in a local dashboard
Apache 2.0, no signup, no API keys beyond what Claude Code already has:
/plugin marketplace add evo-hq/evo
/plugin install evo@evo-hq-evo
United States
NORTH AMERICA
Related News
What Does "Building in Public" Actually Mean in 2026?
19h ago
The Agentic Headless Backend: What Vibe Coders Still Need After the UI Is Done
19h ago
Why Iβm Still Learning to Code Even With AI
21h ago
I gave Claude a persistent memory for $0/month using Cloudflare
1d ago
NYT: 'Meta's Embrace of AI Is Making Its Employees Miserable'
1d ago