limem

A memory system that stores separate Markdown profiles for the user, agent, and project, along with recalled events grouped by how strongly they match. Markdown is plain text with simple formatting.

In plain words
What is it for?
Use it to remember project details, user preferences, agent information, recurring patterns, and relevant past events while working with files and tools.
Why use it?
It helps an agent retain useful context across prompts and sessions instead of relying only on the current conversation.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add gaooooosh/limem-agent-plugin
agentmods
npx agentmods add plugins/gaooooosh/limem-agent-plugin/plugin-src
Clone the repo
git clone --depth 1 https://github.com/gaooooosh/limem-agent-plugin

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

limem scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin-src/.claude-plugin/plugin.json · 44 lines

What it actually says

{
  "name": "limem",
  "version": "0.3.24",
  "description": "Principal-centric LiMem memory model: user / agent / project markdown profiles plus three-tier event recall (hard / pattern / soft) with server-side section scoring.",
  "author": "gaooooosh",
  "homepage": "https://limem.gaooooosh.art",
  "license": "MIT",
  "skills": "skills/",
  "hooks": {
    "UserPromptSubmit": [
      {"hooks": [{"type": "command", "command": "limem hook claude-code UserPromptSubmit"}]}
    ],
    "SessionStart": [
      {"matcher": "startup|resume", "hooks": [{"type": "command", "command": "limem hook claude-code SessionStart"}]}
    ],
    "SessionEnd": [
      {"hooks": [{"type": "command", "command": "limem hook claude-code SessionEnd"}]}
    ],
    "Stop": [
      {"hooks": [{"type": "command", "command": "limem hook claude-code Stop"}]}
    ],
    "PreCompact": [
      {"hooks": [{"type": "command", "command": "limem hook claude-code PreCompact"}]}
    ],
    "PreToolUse": [
      {"matcher": "Edit|Write|NotebookEdit|Bash", "hooks": [{"type": "command", "command": "limem hook claude-code PreToolUse"}]}
    ],
    "PostToolUse": [
      {"matcher": "Edit|Write|NotebookEdit", "hooks": [{"type": "command", "command": "limem hook claude-code PostToolUse"}]}
    ]
  },
  "statusLine": {
    "type": "command",
    "command": "limem-statusline",
    "padding": 0
  },
  "mcpServers": {
    "limem": {
      "command": "limem-mcp",
      "args": []
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 44 lines scan A bc4b03d24379

Subscribe to this mod's changes

limem is a plugin published in the GitHub repository gaooooosh/limem-agent-plugin (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.