Evolving Lite

https://github.com/user-attachments/assets/d7a5847f-c76e-423d-ad96-13b8e1bd382a

Claude Code that learns from you. Install once. Work normally. When you tell Claude it keeps making the same mistake, the system stores that correction, and can feed it back as context before a later tool call.

"I corrected Claude about checking tsconfig strict mode first. A week later, different project, similar type error - Claude checked strict mode before I said anything. That's when I stopped thinking of it as a plugin."

See It In Action

2 min demo: Claude recalls a past decision and a correction is captured and fed back as context.

Self-Star Doctor (/health)

Evolving Lite ships its own install-time health assistant. The Self-Star Doctor runs a synthetic pulse through every junction of the self-improving loop and prints a green/yellow/red board:

 ✓ delegation       GREEN  synthetic prompt -> valid delegation decision row
 ✓ fitness          GREEN  event -> bounded cognitive-fitness score, read back
 ✓ autoevolve       GREEN  optimizer present, kill-switches OK, one scored cycle
 ✓ steward          GREEN  zero false findings on a clean repo
 ✓ verifier-spine   GREEN  EPT spine resolves; markerless claim blocked
 ✓ security         GREEN  tier-check classifies + scanner flags a planted secret
 ✓ kairn-link       GREEN  Kairn installed + reachable

It runs once automatically on your first session and is re-runnable any time with /health. It heals conservatively (creates only missing empty scaffolding, asks before touching settings.json, never overwrites or deletes) and runs its pulse in an isolated scratch copy, so it never touches your real data.

What Makes This Different

Most Claude Code tools add features. Evolving Lite adds feedback loops.

It learns from corrections. From session 3, say "You keep forgetting to check tsconfig first" and the detector recognises the repeat signal and stores it as an experience. From session 10, before Claude runs a Write, Edit, Bash or Task call, the system compares that call's input against your stored experiences and can add up to two matching ones to Claude's context. Matching needs at least two shared keywords, so it is a real filter, not a guarantee. The store lives with the plugin install, so projects sharing that install share it.

It activates progressively. Session 1: safety net only. Session 3: learning kicks in. Session 10: deep memory. You're never overwhelmed, and each tier earns trust before the next one activates.

It heals itself. Every hook writes a sentinel file proving it ran. Run the health-monitor agent to check all sentinels - silent failures don't stay silent.

It gets leaner, not fatter. Low-relevance experiences and stale sessions get archived. The system prunes itself so it stays fast at month 6 the same way it was at day 1.

Self-Evolution is ON

Evolving Lite self-tunes its own delegation config from your sessions out of the box. AutoEvolve watches the outcomes of delegation decisions and adjusts the routing config when it sees a real, repeated signal. This is the headline feature - and it is on by default - so here is exactly how it is kept safe and how to turn it off.