Skip to main content
Glama
tt-a1i
by tt-a1i

remember

Store important context, decisions, and preferences in long-term memory for recall across sessions. Optionally checks for similar existing memories and sensitive data before saving.

Instructions

Store information in long-term memory within a specific space. Use this proactively to save architecture decisions, user preferences, project conventions, bug solutions, and key context. Content is scanned for sensitive patterns (API keys, passwords, tokens) before sending to Cloud. If detected, the write is blocked and findings are returned with a hint on how to proceed. For chat:* spaces, similar existing memories are checked automatically and surfaced as conflicts in the response. Use check_conflicts to override. Content is queued for AI extraction and becomes searchable only after upstream processing completes. For important writes, prefer remember(include_status=true) so the write-after status check runs immediately. Use request_status, recall, or briefing to distinguish queued, provisional, fallback, and searchable states. Set flush=true at end of session or topic switch; flush=false during ongoing work. Provide a description when creating a new space for the first time.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
roleNoMessage role: 'user' or 'assistant'
flushNoWhether to trigger immediate extraction. Default true. Set false only when sending multiple messages in a batch
senderNoBackward-compatible alias. Use 'user'/'assistant' as role alias, or pass a sender user_iduser
contentYesThe information to remember
user_idNoOptional sender user_id override (API sender field)
space_idNoTarget memory space in <domain>:<slug> format (e.g. coding:my-app, chat:preferences, chat:daily, study:ml). Use chat:preferences for durable personal preferences, chat:daily for ongoing chat context, coding:<repo> for project decisions, and study:<topic> for learning notes. If omitted, the server may use EVERMEMOS_DEFAULT_SPACE or auto-detect from the current git remote (coding:<repo-name>).
refer_listNoOptional referenced message ID list
descriptionNoHuman-readable description of this space (recommended when creating a new space)
include_statusNoWhether to also query request status once after queuing the memory write. Recommended for important writes and write-after checks
check_conflictsNoCheck for similar existing memories before storing. Default: auto (enabled for chat:* spaces, disabled for others). When conflicts are found, the new memory is still stored and conflicts are returned for the agent to decide.
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses sensitive-pattern scanning and blocking, automatic conflict checking for chat:* spaces, queued extraction and searchability delays, status-check behavior with include_status, and flush semantics. This goes well beyond a basic 'store information' statement.

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 long but dense with actionable information. Every sentence introduces a distinct behavioral or usage detail—no filler or redundancy. It is front-loaded with the core purpose and then branches into security, conflict handling, processing states, and operational flags, making it easy to locate key points.

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

Completeness5/5

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

Given the tool's complexity (10 parameters, no annotations, no output schema), the description is highly complete. It covers all critical aspects: what to store, space selection, sensitive data handling, asynchronous processing, conflict checking, flush behavior, and status verification. It even guides on when to use sibling tools for state distinction. The lack of a return-value description is mitigated by the detailed write/status behavior described.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful context beyond the schema: it explains space_id domain semantics (coding:<repo>, chat:preferences, etc.), recommends when to set flush=false and include_status=true, and clarifies check_conflicts default behavior. This adds value above the schema's property descriptions.

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's function: 'Store information in long-term memory within a specific space.' It uses a specific verb and resource, and the proactive use cases (architecture decisions, user preferences, project conventions, etc.) distinguish it from sibling tools like recall, briefing, forget, and list_spaces.

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

Usage Guidelines5/5

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

The description provides explicit when-to-use guidance and alternatives. It says 'Use this proactively to save...' and directs users to related tools: 'Use check_conflicts to override,' 'use request_status, recall, or briefing to distinguish states.' It also gives contextual advice on flush behavior, include_status, and space selection, making it clear when and how to use the tool.

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/tt-a1i/everos-mcp'

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