MCP.Market

LLMSlim memory MCP server

by Thanatos9404·io.github.Thanatos9404/llmslim·v0.11.2·21 stars
No reviews yet

Long-term memory and context fitting for agents, with no LLM in the loop. Local SQLite.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Established

21 stars698 downloads/wk

Reviews

Write one

Nobody has reviewed LLMSlim memory yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

LLMSlim memory tools (5, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • fit_context

    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.

  • forgetwrite action

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

  • list_memories

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

  • recall

    Find what earlier conversations said about a question: the stored messages that answer it, whole and under their dates, within a token budget.

  • remember

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

Public scan report

scanner v0.1.10 · 2026-10-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan93 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How LLMSlim memory compares

Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 803 Databases servers
Tools
5
the typical Databases server has 8
Tools that change things
20%
typical: 10%. Fewer write tools means less an agent can break
GitHub stars
21
more than 84% of 601 Databases servers
Downloads a week
698
more than 87% of 315 Databases servers with a package

What its tools let an agent do: 4 read · 1 change

Release history: 2 versions in the registry since 2026-10-17, latest 2026-10-24, typically one every 7 days.

Install LLMSlim memory in Claude Code, Cursor or VS Code

claude mcp add llmslim -- uvx llmslim
Add to Cursor

What the publisher says

From the LLMSlim memory repository's README, as published. We do not edit it. Read it on GitHub

LLMSlim

Long-term memory and context selection for AI agents and coding tools, with no LLM call.

LLMSlim stores what users and agents say word for word, then returns the parts that answer a question within a token budget you set. It runs as an MCP server, a Python library or a small HTTP server.

Examples • Documentation • Live Studio Playground • Sarvam Integration • Benchmarks • Changelog

A real Python session with llmslim 0.11.1 from PyPI, typed by a script and recorded with asciinema (script, recording).

Use it in 30 seconds

Each MCP setup below starts the same server, llmslim mcp, with uv (Python 3.10 or newer). Memory goes to a local SQLite file, ~/.llmslim/memory.db.

One click:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

LLMSlim memory: common questions

Is LLMSlim memory MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the LLMSlim memory safety report
How do I install LLMSlim memory?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does LLMSlim memory need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is LLMSlim memory maintained?
The last commit was 8 days ago (2026-10-24). The latest release is v0.11.2.
What can I use instead of LLMSlim memory?
Servers from other publishers that do the same job: Th Memory MCP server, Remem MCP server and Myc MCP server. Compare all LLMSlim memory alternatives.
How does LLMSlim memory compare with other Databases MCP servers?
safety score 92/100 (higher than 90% of 803 Databases servers); tools 5 (the typical Databases server has 8); tools that change things 20% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to LLMSlim memory

Same job from other publishers: the closest match first, then the best rated.

All LLMSlim memory alternatives →
  • Th Memory
    Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor
    A
  • Remem
    Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.
    B
  • Myc
    Task queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.
    C
  • ZenBrain Memory
    Agent memory: working, episodic, semantic, procedural and core layers. Local SQLite, no account.
    A
  • Memory Arbiter
    Local SQLite MCP memory: evidence-based recall, advisory conflict notices, authorized governance.
    A
LLMSlim memory vs RememLLMSlim memory vs Myc