evoKarpathy-style autoresearch on any codebase: /evo:discover instruments the benchmark, /evo:optimize runs tree search with parallel subagents in worktrees. Plugin for Claude Code, Codex & co.
Why switchSame lineage — Karpathy's autoresearch loop for coding agents. The skill is a single-branch keep/discard hill-climb; evo adds tree search, parallel worktree subagents, shared failure traces, gates and a dashboard. Start with the skill, graduate to evo.
Full comparison → loop-engineeringReference repo plus npm CLIs (loop-init/audit/cost) for loop engineering: designing scheduled, gated control loops that prompt and orchestrate AI coding agents — Grok, Claude Code, Codex — over time.
Why switchBoth operationalize 'the loop is the unit of progress': loop-engineering is the design methodology and CLIs for building gated loops; autoresearch is one specific, proven loop shipped as an installable skill.
Full comparison → siaSelf-improving loop from the SIA paper: Meta, Target and Feedback agents evolve a task agent's harness AND weights against a benchmark — #1 on MLE-Bench Hard, 14x kernel speedups.
Why switchSame lineage — the autoresearch loop: metric, modify, verify, keep or discard. The skill hill-climbs your code with a fixed agent; SIA makes the agent itself the thing that improves, up to and including its weights.
Full comparison → loopyA public library of reusable AI-agent loops plus Loopy, an installable skill that helps agents find, audit, adapt, run and publish loops from the live catalog.
Why switchBoth distribute reusable agent loops: autoresearch is one loop (Karpathy's research iteration) as an installable skill; Loopy is a whole catalog of loops plus find/audit/run tooling.
Full comparison →