# Agent Memory · xultrax-web

> Codify how you work. Every AI tool obeys. Markdown rules + cross-tool companion files (AGENTS.md/CLAUDE.md/.cursor/rules/.gemini) + Compliance Receipts for protocol-level enforcement of destructive ops. Reference implementation of CRP 1.0. Works on every

## Facts
- Page: https://tashan.sh/capability/pkg-xultrax-web-agent-memory-mcp
- tashan id: pkg:@xultrax-web/agent-memory-mcp
- Source: https://github.com/xultrax-web/agent-memory-mcp
- npm: https://www.npmjs.com/package/@xultrax-web/agent-memory-mcp
- Type: npm
- Category: security
- tashan score: 47.0 / 100
- Adoption: 29.0
- Upkeep: 63.0
- Freshness: 75.0
- Evidence coverage: 100% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- npm downloads: 118/week
- License: MIT
- Official: no

## Install

```sh
claude mcp add xultrax-web-agent-memory -- npx -y @xultrax-web/agent-memory-mcp
```

## Security audit
- Known advisories: 0
- Install-time script: none declared
- Build provenance: not attested

Permissions are read from DECLARED dependencies only. Nothing is executed, so an empty result means "nothing declared", never "nothing possible".

---
Measured 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.