recall
Search persistent project memory for past decisions, caveats, and file history before starting tasks to avoid repeating mistakes across AI sessions.
Instructions
Your persistent memory across all AI tools. CALL THIS BEFORE STARTING ANY TASK to check for past caveats (pain records), decisions, and learnings — prevents repeating mistakes across sessions.
Typical usage: recall({ query: "keywords" }) for search, recall({ path: "file.ts" }) for file history, recall() for overview.
WHEN TO CALL: • Before starting any new task or touching a file • When the user mentions "before" / "前に" / "last time" / "remember when" • When an error occurs — check if you've seen it before • When making a decision — check for prior decisions on the same topic
THREE MODES (auto-detected): • Search (default): provide query → returns memories ranked by relevance + heat • File history: provide path → returns complete edit history with user-intent context • Session brief: omit all params → what needs attention (🔴/🟡), where you are on the Map, open loops (proposals / distill queue / friction), top entities. CALL THIS FIRST in a new session. • Locate: where: "" → your position on the Current Truth Map + blast radius (what else moves if you touch this). where: true → auto-locate from recent edits • Dream: dream: true → North Star + orphaned proposals to triage + distill_queue + friction (the full triage session; the brief carries only the counts) • Entity list: overview: true (the old no-arg behaviour)
Works across Claude, GPT, Cursor, Codex, Gemini — one local SQLite file, nothing leaves your machine.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "recall"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| band | No | Filter by heat band. | |
| kind | No | For overview mode: filter by entity kind. | |
| path | No | File path or substring. When set, returns file edit history with per-edit user-intent context instead of memory search. | |
| dream | No | Return the full triage set: North Star, orphaned proposals (each with candidate_id), distill_queue, friction. Resolve proposals with resolve_drift({ candidate_id, action }); rewrite distill items with remember({ memory_id, content }). | |
| layer | No | Layer filter. Accepts aliases (decisions/warnings/how/etc.). | |
| limit | No | Hard cap on results. | |
| query | No | What you want to remember. Use keywords, entity names, or FTS5 expressions. Omit for entity overview. | |
| where | No | Locate on the Current Truth Map. A topic string, or true to auto-locate from the files you edited recently. Returns your node, journey stage, blast radius, and the decision behind it. | |
| offset | No | Skip N results (pagination). | |
| distill | No | With dream: how many raw memories to return for rewriting (default 8, max 25). The queue is value-ordered; rule-verdicted items never appear. | |
| explain | No | Include ranking internals (composite, heat, band, momentum, match_reasons, score_breakdown). Off by default so more memories fit the token budget. | |
| project | No | With where: the Map project slug, when several maps are imported. | |
| altitude | No | Filter by cognitive altitude. | |
| mem_type | No | Filter by memory type. | |
| overview | No | Return the entity list instead of the session brief when no query is given. | |
| mem_state | No | Filter by lifecycle state. | |
| thread_id | No | Filter by thread ID for decision chains. | |
| max_tokens | No | Token budget. Default 2000. | |
| entity_name | No | Narrow to a specific entity | |
| max_intents | No | For file mode: max user-intent snippets. Default 10. | |
| min_memories | No | For overview mode: minimum memory count. Default 1. | |
| mark_accessed | No | Set false for preview queries. | |
| scope_to_roots | No | For file mode: filter to client-provided roots. |