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.
/plugin marketplace add Yupcha/memXTnpx agentmods add plugins/yupcha/memxt/claude-plugingit clone --depth 1 https://github.com/Yupcha/memXTGrade A, and why
memxt 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "memxt",
"displayName": "memxt — Local Memory",
"version": "0.3.3",
"description": "Persistent, private, local-first memory for Claude Code. Your agent remembers your code and decisions across sessions — one static binary, no cloud, nothing leaves your machine.",
"author": { "name": "Yupcha", "url": "https://github.com/Yupcha" },
"homepage": "https://github.com/Yupcha/memxt",
"repository": "https://github.com/Yupcha/memxt",
"license": "MIT",
"keywords": ["memory", "mcp", "local-first", "claude-code", "embeddings", "privacy"],
"mcpServers": "./.mcp.json",
"hooks": "./hooks/hooks.json",
"skills": "./skills/",
"commands": "./commands/"
}
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 · 17 lines scan A ff09fc006390
memxt is a plugin published in the GitHub repository Yupcha/memXT (23 stars, last pushed 1mo 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 2026-08-30.
Other plugins, from other repositories
claude-plugin
Memory for AI coding agents: your own past sessions, recalled before you ask.
iai-pme
The personal memory engine for AI coding assistants — local, encrypted, verbatim.
iai-memory
Persistent local memory for your assistant: every turn captured verbatim, relevant memory injected at session start and before each turn, and fifteen memory tools over MCP. Requires the iai-pme package (pip install iai-pme).
emulo
Emulo: mine your local AI coding session logs into a personal profile your agent loads before every task.
emulo
Mine real AI coding sessions into a bounded, evidence-backed personal layer.
perenna
A lightweight, Git-backed permanent memory for AI agents.