What is mubit-memory?

A Claude Code plugin that stores and recalls typed long-term memories through Mubit, an external memory service. It also records lessons and their outcomes.

Use it to recall relevant past lessons, capture work-related memories, and attribute outcomes so later assistance can improve.

It helps preserve useful context between coding sessions instead of relying only on the current conversation.

mubit-memory — Plugin by mubit-ai

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 mubit-ai/claude-plugins

agentmods

npx agentmods add plugins/mubit-ai/claude-plugins/claude-code

Clone the repo

git clone --depth 1 https://github.com/mubit-ai/claude-plugins

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

mubit-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 2d ago.

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.

integrations/claude-code/.claude-plugin/plugin.json · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "mubit-memory",
  "displayName": "Mubit Memory",
  "version": "0.12.4",
  "description": "Persistent, typed, self-improving memory for Claude Code, backed by Mubit. Captures work involuntarily, recalls relevant lessons before every prompt, and attributes outcomes so memory improves with use.",
  "author": { "name": "Mubit AI", "url": "https://mubit.ai" },
  "homepage": "https://docs.mubit.ai/integrations/claude-code",
  "repository": "https://github.com/mubit-ai/claude-plugins",
  "license": "Apache-2.0",
  "keywords": ["memory", "mubit", "long-term-memory", "lessons", "recall", "rag"],
  "userConfig": {
    "endpoint": { "type": "string", "title": "Mubit endpoint", "default": "",
      "description": "Your Mubit instance URL, e.g. https://api.mubit.ai. Required." },
    "apiKey": { "type": "string", "title": "API key", "default": "", "sensitive": true,
      "description": "Mubit API key (mbt_...). Set here, it is held in the OS keychain; /mubit-memory:auth stores it in the plugin's own data directory, readable only by you. Never in a settings file." },
    "userId": { "type": "string", "title": "User id", "default": "",
      "description": "Optional user/entity id for multi-user memory scoping. This is a retrieval scope, not a name: set it and recall only sees memory captured under the same value." },
    "actorId": { "type": "string", "title": "Actor id", "default": "",
      "description": "Who captured memory is attributed to. Leave blank and it is detected once per month from github.user, your git commit email or $USER, and recorded as a label on each memory. Unlike userId it never narrows what recall can see." },
    "runStrategy": { "type": "string", "title": "Run strategy", "default": "per-directory",
      "description": "How a Claude Code session maps to a Mubit run: per-directory, git-branch, per-conversation, or static." },
    "capture": { "type": "boolean", "title": "Capture tool activity", "default": true,
      "description": "Capture t

Read the full file on GitHub · 62 lines

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.

2d ago First seen · 62 lines scan A e9fc57647f62

Subscribe to this mod's changes

mubit-memory is a plugin published in the GitHub repository mubit-ai/claude-plugins (13 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.

Data and AI Learning and teaching Memory and context

mubit-memory

Getting it into your agent

Grade A, and why

Nothing flagged

How it starts

What this file has done since we first saw it

Other plugins, from other repositories

claude-code-plugin

edulab

Master-skill

ida-plugin-development

cortex

hello-world