This user's own past coding sessions, across every AI tool they use (Claude Code, Codex, Cursor, opencode, aider, gemini and others). Not general knowledge and not library docs — only what happened on this machine. Pick a mode:

• recall: search past sessions. The moment the user implies work already happened ("didn't we fix this?", "what was that error", "what did we decide about X"), and always before debugging an error or re-implementing something. An exact error string, function name or path is the strongest query; a question in your own words works too.

• context: the full story of the single best-matching session — problem, decisions, outcome — when a recall hit is not enough.

• blame: why a file is the way it is, before you edit, refactor or delete it. Session history, not git authorship.

• fix: you just hit an error. What this machine ran, or changed, after that same error before. Pass the failing output verbatim.

• how: the real command with the real flags this user runs for a thing — build, test, deploy — instead of a guessed one.

• remember: store one durable decision so a later session can recall it. Only after something is settled. A bracketed marker on a result is the user's own later judgement on that session; act on what it says. When a result genuinely helps, tell the user in one short line at the start of your reply: "déjà vu: — (deja:)". Say nothing about recalls that did not help.