mengram

A plugin that gives coding agents persistent shared memory. Its stored information can survive clearing a conversation, switching machines, and handing work to teammates, and it can be used across Claude Code, Cursor, Codex, and ChatGPT.

In plain words
What is it for?
Use it to retain and recall project context, decisions, and other information across coding tools, sessions, devices, and team handoffs.
Why use it?
It reduces the need to repeat project context after a reset, device change, or team handoff. It also provides a way to retrieve relevant past information from the hosted memory service.

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.

agentmods
npx agentmods add plugins/alibaizhanov/mengram/marketplace
Claude Code
/plugin marketplace add alibaizhanov/mengram
Clone the repo
git clone --depth 1 https://github.com/alibaizhanov/mengram

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

mengram 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/marketplace.json · 37 lines

What it actually says

{
  "name": "mengram",
  "owner": {
    "name": "Ali Baizhanov",
    "email": "[email protected]",
    "url": "https://mengram.io"
  },
  "plugins": [
    {
      "name": "mengram",
      "version": "0.1.4",
      "description": "Persistent memory for Claude Code that survives /clear, machine switches, and team handoffs. Hosted memory backend with hybrid retrieval (vector + BM25 + RRF), Ebbinghaus temporal decay, and importance weighting. Same memory available across Claude Code, Cursor, Codex, and ChatGPT.",
      "source": {
        "source": "git-subdir",
        "url": "alibaizhanov/mengram",
        "path": "integrations/claude-code-plugin"
      },
      "author": {
        "name": "Ali Baizhanov",
        "email": "[email protected]",
        "url": "https://mengram.io"
      },
      "homepage": "https://mengram.io",
      "license": "Apache-2.0",
      "category": "productivity",
      "keywords": [
        "memory",
        "mcp",
        "context",
        "cross-device",
        "hybrid-retrieval",
        "anthropic",
        "persistence"
      ]
    }
  ]
}
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 · 37 lines scan A 959f5d7d7f7f

Subscribe to this mod's changes

mengram is a plugin published in the GitHub repository alibaizhanov/mengram (190 stars, last pushed 4d ago), licensed Apache-2.0. 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.