Skip to main content
Glama

search_memory

Find relevant past memories using hybrid vector and keyword search. Filter by date, category, or topic to retrieve context when debugging, writing, or referencing previous work.

Instructions

Search indexed memories by hybrid relevance (vector + BM25 + reranking) and return ranked results with optional temporal filtering. The shown score is a fused ranking score (0-100%), NOT pure cosine similarity — read it as relative ranking within this result set, not as match confidence. Read-only, but may fire stored reminders as a side effect. Use proactively at the start of tasks, when debugging, writing, or when the user references past work.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query — natural language or keywords
limitNoMax results to return
scopeNoOptional explicit scope
sessionIdNoOptional session identifier to infer session:<id> scope
allScopesNoWhen true, explicitly allow cross-scope search
categoryNoFilter by memory category: profile (identity/background), preferences (habits/style), entities (projects/tools/people), events (past happenings), cases (problem-solution pairs), patterns (reusable workflows)
profileNoRetrieval profile
renderNoResult rendering mode: verbatim (default, original order) or highlight (reorder by contextual relevance to query)verbatim
afterNoFilter memories stored after this date (ISO format YYYY-MM-DD, or relative like '最近30天', 'last 7 days')
beforeNoFilter memories stored before this date (ISO format YYYY-MM-DD, or relative)
graphNoEnable KG graph traversal (PPR) for relationship-aware search. Use when query involves entity relationships (e.g. 'what tools does Alice use', 'Bob的朋友').
includeArchivedNoWhen true, also return archived/superseded/consolidated memories (default: only active)
detail_levelNoResult detail level: brief (ID+score+one-liner), normal (default, current behavior), full (include metadata)normal
topicTagNoFilter by topic tag (e.g. 'auth', 'deploy', 'testing'). Only returns memories tagged with this topic.
reconstructNoReturn LLM-synthesized reconstruction alongside raw results. Requires RECALLNEST_CONSTRUCTIVE_RETRIEVAL=true.
validAtNoQuery memories valid at a specific point in time (ISO date, e.g. '2025-06-15'). Returns only memories whose validity window covers this date.
includeExpiredNoWhen true, include expired memories in results (demoted 80%). Default: only active/non-expired.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses that the score is a fused ranking (0-100%) not pure cosine similarity, and that the tool is read-only but may fire reminders as a side effect. This adds significant transparency beyond basic read operation, though more details on rate limits or auth could improve.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four sentences, each earning its place: core function with technique, score interpretation, side-effect disclosure, and usage guidance. No fluff, well-structured, and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 17 parameters and no output schema, the description covers main purpose, score semantics, side effect, and usage context. It does not detail output format, but the schema and context signals partially compensate. It is nearly complete for an agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions for all 17 parameters. The tool description does not add additional parameter-specific meaning beyond what the schema already provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches indexed memories using hybrid relevance (vector + BM25 + reranking) and returns ranked results with temporal filtering. It specifies the resource (memories) and action (search) with technical detail, distinguishing it from sibling tools that perform other memory operations like storing or forgetting.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly advises proactive use at task start, debugging, writing, and when referencing past work. While it provides clear context for when to use, it does not contrast with alternatives like retrieve_skill or memory_drill_down, but the guidance is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AliceLJY/recallnest'

If you have feedback or need assistance with the MCP directory API, please join our Discord server