# Recall

Search agentmemory for past observations, sessions, and learnings about a topic using...

- Repository: https://github.com/rohitg00/agentmemory (30072 stars)
- Category: Engineering
- License: Apache-2.0
- Last updated: 2026-10-29
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add rohitg00/agentmemory --skill recall -g -a claude-code -y`
Codex: `npx skills add rohitg00/agentmemory --skill recall -g -a codex -y`
Cursor: `npx skills add rohitg00/agentmemory --skill recall -g -a cursor -y`
Gemini CLI: `npx skills add rohitg00/agentmemory --skill recall -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add rohitg00/agentmemory`

## Description

Search agentmemory for past observations, sessions, and learnings about a topic using hybrid BM25 plus vector plus graph search. Use when the user says "recall", "what did we do about", "did we ever", "have we seen", or needs context from past sessions.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

The user wants to recall past context about: $ARGUMENTS

## Quick start

```json
memory_smart_search { "query": "jwt refresh token rotation", "limit": 10 }
```

Expected output:

```text
2 results across 2 sessions.
[importance 8] decision · "Rotate refresh tokens on every use" (session 7f3a9c21)
[importance 5] code · "limit.ts counts per-IP" (session b21d004e)
```

## Why

Only surface what the tool returned. Never fabricate an observation, a session
id, or an importance score. If nothing comes back, say so.

## Workflow

1. Call `memory_smart_search` with the user's text as `query` and `limit: 10`.
   Pass `project` when the user scopes to a specific repo and `agentId` when
   they request one agent's history.
   Use `targetLayer: "memory"` for explicitly saved knowledge, or
   `targetLayer: "observation"` for captured activity. Omit it for mixed search.
2. Search results are compact. Before quoting full content or describing
   provenance, call `memory_smart_search` with the selected IDs as a
   comma-separated `expandIds` string and the same project, agent, and layer
   filters. If expansion fails or the record is no longer available, report
   that limitation; a title alone is not the full fact.
3. Group expanded observations by session and show the returned type, title,
   and narrative. Include provenance only when the response supplies it.
4. Lead with the high-signal observations (importance >= 7).
5. With `memory_recall`, inspect `matched_count`, `excluded_by_budget`, and
   `content_truncated` before treating an empty or shortened response as absent
   knowledge. Recover full content with `memory_smart_search` using `expandIds`
   and the same project, agent, and layer filters. `minimum_budget` reports the
   estimated budget needed for a minimal preview when the budget is too small.
6. If there are no matches, suggest 2-3 alternative search terms and stop. Do not guess.

## Anti-patterns

The rest: https://github.com/rohitg00/agentmemory/blob/HEAD/plugin/skills/recall/SKILL.md