Oh My ExperienceStop teaching your agent the same lesson twice.

Turn real coding corrections into reviewed experience cards that surface at prompt time — only when the task actually needs them.

Conditional recall, not always-on bloat

Hook decomposes prompts into task envelopes with deterministic BM25-like matching. Cards inject only when triggered — otherwise nothing.

Cards follow candidate → draft → active → archived. AI-generated candidates go through your approval first. Only active cards are recalled.

Same cards, same retrieval engine, shared across providers. Install each hook once.

Everything on your machine. No cloud, no accounts. The hook path calls no LLM, stores no raw prompts.

Use ome match --explain to see which cards hit, why they scored, and what context would be injected.

AGENTS.md injects once then gets compressed away. OME's hook re-injects on every UserPromptSubmit.