memo

A local memory plugin for AI agents that stores searchable notes on disk and uses local machine-learning models. It supports Apple Silicon and Linux/Ubuntu setups without cloud APIs or Ollama.

In plain words
What is it for?
Use it to save and search agent memories through an Obsidian vault and a local vector database.
Why use it?
It lets agents retrieve past information while keeping the memory store and processing on the local machine.

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 jagoff/memo
agentmods
npx agentmods add plugins/jagoff/memo/memo
Clone the repo
git clone --depth 1 https://github.com/jagoff/memo

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

memo 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.

.claude-plugin/plugin.json · 15 lines

What it actually says

{
  "name": "memo",
  "description": "Local MCP memory for AI agents — MLX on Apple Silicon or CPU sentence-transformers on Linux/Ubuntu, sqlite-vec store, markdown-on-disk in your Obsidian vault. Zero Ollama, zero cloud APIs.",
  "version": "4.14.10",
  "author": {
    "name": "Fernando Ferrari",
    "email": "[email protected]",
    "url": "https://github.com/jagoff"
  },
  "homepage": "https://github.com/jagoff/memo",
  "repository": "https://github.com/jagoff/memo",
  "license": "MIT",
  "keywords": ["memory", "mcp", "mlx", "obsidian", "rag", "agents", "local-first"]
}
Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 15 lines scan A 4bafe4f3db9b

Subscribe to this mod's changes

memo is a plugin published in the GitHub repository jagoff/memo (16 stars, last pushed yesterday), 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 2026-08-30.