codies-memory

A file-based memory system that lets AI agents save and retrieve information between sessions, with separate storage areas and trust levels.

In plain words
What is it for?
Use it to store agent notes, identities, trusted information, and general shared notes through command-line write operations.
Why use it?
It prevents useful context from disappearing when a session ends and helps keep one agent's notes separate from another's.

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 pyros-projects/limitless
agentmods
npx agentmods add plugins/pyros-projects/limitless/codies-memory
Clone the repo
git clone --depth 1 https://github.com/pyros-projects/limitless

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

codies-memory 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.

plugins/codies-memory/.claude-plugin/plugin.json · 21 lines

What it actually says

{
  "name": "codies-memory",
  "version": "1.2.2",
  "description": "File-based two-tier memory system for AI agents. Agent-namespaced vaults with promotion pipelines, trust levels, CLI write commands, and explicit _general read mode for vault-less notes. Gives any agent persistent memory across sessions.",
  "author": {
    "name": "Pyro"
  },
  "homepage": "https://github.com/pyros-projects/limitless",
  "repository": "https://github.com/pyros-projects/limitless",
  "license": "MIT",
  "keywords": [
    "memory",
    "persistence",
    "identity",
    "agent-memory",
    "vault",
    "promotion",
    "trust"
  ]
}
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 · 21 lines scan A 8b6c1d616082

Subscribe to this mod's changes

codies-memory is a plugin published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 19d 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.