# LLMSlim memory (pypi · llmslim)

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

- Trust score: 78/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- pypi · `llmslim`: 78/100 (this document), [markdown](https://verifymcp.io/servers/thanatos9404-llmslim/llmslim.md), [page](https://verifymcp.io/servers/thanatos9404-llmslim/llmslim)

## Channel facts

- Registry: `pypi`
- Package: `llmslim`
- Version: `0.11.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 0 of 13 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Thanatos9404/llmslim).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 542 tokens (~108/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the LLMSlim memory MCP server?

LLMSlim memory runs locally as a PyPI package, launched with uvx llmslim. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add thanatos9404-llmslim -- uvx llmslim
```

### Cursor

```json
{
  "mcpServers": {
    "thanatos9404-llmslim": {
      "command": "uvx",
      "args": [
        "llmslim"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "thanatos9404-llmslim": {
      "command": "uvx",
      "args": [
        "llmslim"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add thanatos9404-llmslim -- uvx llmslim
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "thanatos9404-llmslim": {
      "type": "local",
      "command": [
        "uvx",
        "llmslim"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add thanatos9404-llmslim --command uvx --arg llmslim
```

### Hermes

```yaml
mcp_servers:
  thanatos9404-llmslim:
    command: "uvx"
    args: ["llmslim"]
```

### Netclaw

```json
{
  "McpServers": {
    "thanatos9404-llmslim": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "llmslim"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add thanatos9404-llmslim -t stdio -c uvx -a llmslim
```

### Other

```json
{
  "mcpServers": {
    "thanatos9404-llmslim": {
      "command": "uvx",
      "args": [
        "llmslim"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 78, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-17 (score 63)

First indexed and scored.

## MCP tools (5)

### `remember` (~92 tokens)

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.

Input parameters:

- `role` (string)
- `session`
- `text` (string, required)

Output parameters:

- `result` (string)

### `recall` (~97 tokens)

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

Input parameters:

- `budget` (integer)
- `query` (string, required)
- `session`

Output parameters:

- `result` (string)

### `list_memories` (~61 tokens)

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.

Input parameters:

- `limit` (integer)
- `session`

Output parameters:

- `result` (string)

### `forget` (~52 tokens)

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.

Input parameters:

- `memory_id` (string, required)

Output parameters:

- `result` (string)

### `fit_context` (~101 tokens)

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.

Input parameters:

- `budget` (integer)
- `query`
- `text` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/thanatos9404-llmslim/llmslim#diagnostics

## Score history

- 2026-10-18: 78
- 2026-10-17: 63

## Common questions

### What is the LLMSlim memory MCP server?

LLMSlim memory is an MCP server listed in the public MCP registry as io.github.Thanatos9404/llmslim. Long-term memory and context fitting for agents, with no LLM in the loop. Local SQLite. This page covers its PyPI package (llmslim).

### Is the LLMSlim memory MCP server safe to use?

LLMSlim memory scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the LLMSlim memory MCP server expose?

LLMSlim memory exposes 5 tools: remember, recall, list_memories, forget, fit_context. Their descriptions and schemas cost roughly 403 tokens of context every time the server is loaded.

### Is the LLMSlim memory MCP server still maintained?

LLMSlim memory is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the LLMSlim memory MCP server under?

LLMSlim memory declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/llmslim/
- Socket report: https://socket.dev/pypi/package/llmslim
- Repository: https://github.com/Thanatos9404/llmslim
- Website: https://llmslim.app/
- Changelog RSS feed: https://verifymcp.io/servers/thanatos9404-llmslim/llmslim.xml
- Changelog JSON feed: https://verifymcp.io/servers/thanatos9404-llmslim/llmslim.json
- HTML version of this page: https://verifymcp.io/servers/thanatos9404-llmslim/llmslim