
Recall
- 9.1k installs
- 26.6k repo stars
- Updated August 3, 2026
- rohitg00/agentmemory
A skill that searches agentmemory's stored observations and sessions using hybrid search (BM25 + vector + graph) to retrieve relevant past context
About
The recall skill searches agentmemory using hybrid BM25 plus vector plus graph search to retrieve past observations, sessions, and learnings. Developers invoke it when users ask 'recall', 'what did we do about', 'did we ever', or need context from previous sessions. It calls memory_smart_search with a query and limit, returning results grouped by session with importance scores and observation types (decision, code, etc). High-importance observations (>= 7) are surfaced first. When no results are found, it suggests 2-3 alternative search terms instead of fabricating context.
- Hybrid search combining BM25, vector, and graph algorithms for context retrieval
- Groups results by session showing observation type, title, narrative, and importance scores
- Surfaces high-signal observations (importance >= 7) first in result sets
- Suggests alternative search terms when queries return zero results
- Never fabricates session ids, importance scores, or observations not returned by the tool
Recall by the numbers
- 9,101 all-time installs (skills.sh)
- +652 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #93 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: HIGH risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
recall capabilities & compatibility
- Capabilities
- hybrid search · session grouping · importance ranking · multi session retrieval · alternative term suggestion
- Use cases
- memory · research · planning
What recall says it does
Search agentmemory for past observations, sessions, and learnings about a topic using hybrid BM25 plus vector plus graph search
If zero results, suggest 2-3 alternative search terms and stop. Do not guess.
Never fabricate an observation, a session id, or an importance score. If nothing comes back, say so.
npx skills add https://github.com/rohitg00/agentmemory --skill recallAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 9.1k |
|---|---|
| repo stars | ★ 26.6k |
| Security audit | 2 / 3 scanners passed |
| Last updated | August 3, 2026 |
| Repository | rohitg00/agentmemory ↗ |
What it does
Retrieve past observations, decisions, and session context from agentmemory using hybrid search across sessions.
Who is it for?
Retrieving past decisions, code references, or session context when users explicitly request recall or when past context is needed
Skip if: Storing new memories (use remember), viewing current session (use recap/session-history), or when no historical context exists
When should I use this skill?
User says 'recall', 'what did we do about', 'did we ever', 'have we seen', or needs information from previous sessions
What you get
Agent retrieves grouped, ranked observations from past sessions with importance scores, enabling context-aware responses grounded in history
- Grouped search results by session
- Importance-ranked observations
- Alternative search term suggestions on empty results
By the numbers
- Default limit of 10 results per search
- Observations with importance >= 7 are considered high-signal
- Returns results across multiple sessions with grouping
Files
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. 2. Group results by session. 3. For each observation show its type, title, and narrative. 4. Lead with the high-signal observations (importance >= 7). 5. If zero results, 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.
Troubleshooting
See ../_shared/TROUBLESHOOTING.md if memory_smart_search is not available.
recall worked examples
1. Hit on a past decision
User: "Did we ever decide how to cache sessions?"
Invocation:
memory_smart_search { "query": "session caching decision", "limit": 10 }Response:
{
"results": [
{ "sessionId": "7f3a9c21", "type": "decision", "title": "Drop Redis for iii state store",
"narrative": "We decided to drop Redis and use the iii-engine state store for session caching.",
"importance": 8 }
]
}Present:
Yes. In session 7f3a9c21 you decided to drop Redis and use the iii-enginestate store for session caching (importance 8).
2. Multiple results across sessions
User: "Recall anything about the rate limiter."
Invocation:
memory_smart_search { "query": "rate limiter", "limit": 10 }Response:
{
"results": [
{ "sessionId": "b21d004e", "type": "code", "title": "limit.ts counts per-IP",
"narrative": "Rate limiter counts per-IP, not per-user.", "importance": 6 },
{ "sessionId": "c98f1100", "type": "conversation", "title": "Discussed sliding window",
"narrative": "Considered a sliding-window limiter, deferred.", "importance": 4 }
]
}Present them grouped by session, leading with the per-IP code note.
3. No results
User: "Recall the GraphQL schema migration."
Invocation:
memory_smart_search { "query": "graphql schema migration", "limit": 10 }Response:
{ "results": [] }Present:
No memories matched that. Tryschema change,graphql, ormigrationas
narrower terms, or recap this week to scan recent sessions.Related skills
FAQ
What does recall return when no results are found?
It suggests 2-3 alternative search terms and stops. It never fabricates observations, session ids, or importance scores.
How are recall results organized?
Results are grouped by session with high-importance observations (>= 7) shown first. Each shows type, title, narrative, and importance score.
What search algorithms does recall use?
Hybrid search combining BM25 (keyword), vector (semantic), and graph algorithms to find relevant past context.
Is Recall safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.