Skip to main content
Glama
Sign In
llmslim

llmslim

by Thanatos9404
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLMSLIM_USER_IDNoWhose memory this server holds. The server fixes this scope, so the model cannot read another user's memory. Default: default
LLMSLIM_AGENT_IDNoOptional agent id, so each agent keeps its own memory.
LLMSLIM_MEMORY_DBNoSQLite file or postgresql:// URL for the memory. Default: ~/.llmslim/memory.db

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
rememberA

Store a message in long-term memory, word for word.

    Args:
        text: The message to keep, in the speaker's own words.
        role: Who said it: "user" (default) or "assistant".
        session: Optional id of the conversation it belongs to. Messages without one are grouped by day.
recallA

Find what earlier conversations said about a question: the stored messages that answer it, under their dates and whole where they fit (the most relevant parts of longer ones), within a token budget.

    Args:
        query: The question, e.g. the user's latest message.
        budget: Most tokens to return. Defaults to the server's budget.
        session: Optional conversation id to search only that conversation.
list_memoriesA

List the most recently stored messages with their ids, newest first.

    Args:
        limit: How many to list, at most 100.
        session: Optional conversation id to list only that conversation.
forgetA

Delete one stored message by its id (from remember or list_memories). This cannot be undone.

    Args:
        memory_id: The id of the message to delete.
fit_contextA

Shrink a long text (a document, log or tool output) to a token budget, keeping the parts that answer the query, in their original order. Text that already fits comes back unchanged.

    Args:
        text: The text to shrink.
        budget: Most tokens to return.
        query: Optional question; the parts that answer it are kept first.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 5 tools

Disambiguation4/5

The tools mostly target distinct actions: remember stores, forget deletes, list_memories lists, recall searches stored memories, and fit_context shrinks arbitrary text. recall and list_memories both retrieve stored memories, but their descriptions distinguish query-based search from chronological listing with ids.

Naming Consistency4/5

All names are snake_case and verb-first, giving a predictable overall pattern. The minor deviation is that remember, recall, and forget are bare verbs while fit_context and list_memories use verb_noun forms, but this remains readable and consistent enough.

Tool Count5/5

Five tools is well-scoped for a memory/context server: store, search, list, delete, and compress context. Each tool earns its place without redundancy or obvious padding.

Completeness4/5

The core memory lifecycle is covered: create with remember, read/search with recall and list_memories, delete with forget, plus fit_context for text compression. The main gap is the lack of an update/edit operation for stored messages, though forget plus remember provides a workaround.

Maintenance

ActivityActive
ResponsivenessLimited data

Resources