SkillHub

Skills rohitg00 agentmemory agentmemory

recall

Use it when:
You ask "what did we do about", "did we ever" or "have we seen" something in past sessions.
It does:
Runs agentmemory's hybrid keyword, vector and graph search, then fetches the full records of the results it quotes.
You get:
Matches grouped by session, highest importance first, or two or three other search terms when nothing matches.
Needs:
agentmemory's memory server running, with its MCP tools connected to your agent.
Never:
Invents an observation, session id or score the search didn't return.

Skill 2 of 8 in the agentmemory bundle, after handoff and before remember.

TL;DR

Part of agentmemory, a memory server that keeps what coding agents learn across sessions. recall is its read side. The agent searches with your words, scoped to a project or to one agent's history when you ask, and to saved memories, captured activity, or both. Search results are compact, so before quoting a fact or saying where it came from it fetches the full records; a title alone isn't treated as the fact, and a record that can't be fetched is reported as such. Results are grouped by session with their type, title and narrative, leading with those of importance 7 or more. When a response was cut short by its token budget, it checks how many results matched or were left out before calling something absent. The rule throughout is to show only what the tool returned: an empty search gets alternative search terms, never a guess at what was discussed.

Summarizes the skill at f0f7378.

npx skills add https://github.com/rohitg00/agentmemory --skill recall

skills.sh pageSource on GitHubAll skills from rohitg00/agentmemory

Total Downloads
14,500 on skills.sh, Nov 9, 2026
Repo stars
30,216 rohitg00/agentmemory
First seen
Apr 7, 2026 on skills.sh
Weekly Downloads
265
-34% over the 8 weeks to Nov 9
Weekly values
Week toInstalls
Sep 21403
Sep 28378
Oct 5349
Oct 12331
Oct 19346
Oct 26319
Nov 2307
Nov 9265
Category
category:agentscategory:software-engineering

Build agents, orchestrate workers and give agents memory.

Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type
type:tool

Operates a CLI, API, app or bundled script to get something done.
Effect
effect:none

Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code.
Needs
needs:mcp

Needs an MCP server connected.
Publisher
by:official

A verified publisher on skills.sh, or the company or maintainer behind the product the skill operates.
Topics
memory
Stack
stack:agentmemory

SKILL.md

From rohitg00/agentmemory at f0f7378. Checked daily, last changed Nov 6, 2026.

Frontmatter
name: recall
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.
argument-hint: "[search query]"
user-invocable: true

The user wants to recall past context about: $ARGUMENTS

Quick start

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

Expected output:

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

WRONG: results are empty, so you write "We probably discussed token expiry last week" from assumption.

RIGHT: "No memories matched that query. Try refresh token, session expiry, or auth rotation."

Checklist

  • Every observation shown came from the tool response.
  • Results grouped by session, high-importance first.
  • Empty results trigger alternative-term suggestions, not invention.
  • No session id or score was paraphrased or rounded.

See also

  • remember: the write side; recall retrieves what it stores.
  • recap, handoff, session-history: session-scoped views of the same data.
  • memory-discipline: when to run this search unprompted.

Troubleshooting

See TROUBLESHOOTING.md if memory_smart_search is not available.