claude-memory

A project memory add-on that stores and retrieves information from earlier coding sessions. It keeps different kinds of memory, including past events, useful procedures, current work, and recurring patterns.

In plain words
What is it for?
Use it to remember project-specific decisions, session summaries, working context, troubleshooting information, and patterns across sessions.
Why use it?
It reduces the need to repeat project background after a new session and helps recover relevant context when errors occur.

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 d2a8k3u/claude-code-memory
agentmods
npx agentmods add plugins/d2a8k3u/claude-code-memory/claude-code-memory
Clone the repo
git clone --depth 1 https://github.com/d2a8k3u/claude-code-memory

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

claude-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.

.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "claude-memory",
  "description": "Fully automatic per-project cognitive memory. Auto-loads git-aware context at session start, auto-saves session summaries, auto-recalls on errors, and auto-consolidates every 10 sessions. 9 MCP tools for episodic, semantic, procedural, working, and pattern memories with hybrid FTS5 + vector search.",
  "version": "1.2.0",
  "author": {
    "name": "David Kulhanek"
  },
  "license": "MIT",
  "keywords": ["memory", "context", "persistence", "embeddings", "knowledge-graph"]
}
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 · 11 lines scan A d22908b6269e

Subscribe to this mod's changes

claude-memory is a plugin published in the GitHub repository d2a8k3u/claude-code-memory (7 stars, last pushed 2mo 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.