mex

Install

The npm package is named mex-agent (mex was taken on npm). The CLI command is mex.

npx mex-agent setup

That's it. The setup command creates the .mex/ scaffold, asks which AI tool you use, pre-scans your codebase, and generates a targeted prompt to populate everything. Takes about 5 minutes.

At the end of setup, you'll be asked to install mex globally. If you accept:

mex check        # drift score
mex sync         # fix drift

If you skip global install, everything still works via npx:

npx mex-agent check        # drift score
npx mex-agent sync         # fix drift

You can install globally later at any time:

npm install -g mex-agent

Drift Detection

Eight checkers validate your scaffold against the real codebase. Zero tokens, zero AI.

| Checker | What it catches | |---------|----------------| | path | Referenced file paths that don't exist on disk | | edges | YAML frontmatter edge targets pointing to missing files | | index-sync | patterns/INDEX.md out of sync with actual pattern files | | staleness | Scaffold files not updated in 30+ days or 50+ commits | | command | npm run X / make X referencing scripts that don't exist | | dependency | Claimed dependencies missing from package.json | | cross-file | Same dependency with different versions across files | | script-coverage | package.json scripts not mentioned in any scaffold file |

Scoring: starts at 100. Deducts -10 per error, -3 per warning, -1 per info.

CLI

All commands run from your project root. If you didn't install globally, replace mex with npx mex-agent.

Commands

| Command | What it does | |---------|-------------| | mex | Open the interactive terminal dashboard | | mex tui | Open the interactive terminal dashboard explicitly | | mex setup | First-time setup — create .mex/ scaffold and populate with AI | | mex setup --mode agent-memory | Create templates for persistent-agent / homelab memory workspaces | | mex setup --dry-run | Preview what setup would do without making changes | | mex check | Run drift checkers, output drift score and categorized issues | | mex check --quiet | One-liner: mex: drift score 92/100 (1 warning) | | mex check --json | Full report as JSON for programmatic use | | mex check --fix | Check and jump straight to sync if errors found | | mex sync | Detect drift → choose mode → AI fixes → verify → repeat | | mex sync --dry-run | Preview targeted prompts without executing | | mex sync --warnings | Include warning-only files in sync | | mex init | Pre-scan codebase, build structured brief for AI | | mex init --json | Raw scanner brief as JSON | | mex log <message> | Append a note, decision, risk, or todo to .mex/events/decisions.jsonl | | mex timeline | View recent event log entries | | mex heartbeat | Run lightweight persistent-agent health checks once | | mex doctor | Friendly scaffold health summary | | mex watch | Install post-commit hook (silent on perfect score) | | mex watch --interval | Run heartbeat repeatedly in the foreground | | mex watch --uninstall | Remove the hook | | mex completion <shell> | Print bash, zsh, or fish completions | | mex commands | List all commands and scripts with descriptions |

Running check after drift is fixed by sync

Before / After

Real output from testing mex on Agrow, an AI-powered agricultural voice helpline (Python/Flask, Twilio, multi-provider pipeline).

Scaffold before setup:

## Current Project State
<!-- What is working. What is not yet built. Known issues.
     Update this section whenever significant work is completed. -->

Scaffold after setup:

## Current Project State

**Working:**
- Voice call pipeline (Twilio → STT → LLM → TTS → response)
- Multi-provider STT (ElevenLabs, Deepgram) with configurable selection
- RAG system with Supabase pgvector for agricultural knowledge retrieval
- Streaming pipeline with barge-in support

**Not yet built:**
- Admin dashboard for call monitoring
- Automated test suite
- Multi-turn conversation memory across calls

**Known issues:**
- Sarvam AI STT bypass active — routing to ElevenLabs as fallback

Patterns directory after setup:

patterns/
├── add-api-client.md       # Steps, gotchas, verify checklist for new service clients
├── add-language-support.md  # How to extend the 8-language voice pipeline
├── debug-pipeline.md        # Where to look when a call fails at each stage
└── add-rag-documents.md     # How to ingest new agricultural knowledge

Real World Results

Independently tested by a community member on OpenClaw across 10 structured scenarios on a homelab setup (Ubuntu 24.04, Kubernetes, Docker, Ansible, Terraform, networking, monitoring). 10/10 tests passed. Drift score: 100/100.

Token usage before vs after mex:

| Scenario | Without mex | With mex | Saved | |----------|------------|---------|-------| | "How does K8s work?" | ~3,300 tokens | ~1,450 tokens | 56% | | "Open UFW port" | ~3,300 tokens | ~1,050 tokens | 68% | | "Explain Docker" | ~3,300 tokens | ~1,100 tokens | 67% | | Multi-context query | ~3,300 tokens | ~1,650 tokens | 50% |

~60% average token reduction per session.

Context is no longer all-or-nothing — loaded on demand, only what's relevant.

How It Works

Session starts
    ↓
Agent loads CLAUDE.md (auto-loaded, lives at project root)
    ↓
CLAUDE.md says "Read .mex/ROUTER.md before doing anything"
    ↓
ROUTER.md routing table → loads relevant context file for this task
    ↓
context file → points to pattern file if task-specific guidance exists
    ↓
Agent executes with full project context, minimal token cost
    ↓
After task: agent runs GROW
    ↓
New patterns, updated project state — scaffold grows from real work

CLAUDE.md stays small. The agent navigates to only what it needs. After meaningful work, it runs GROW: Ground what changed, Record current truth in the scaffold, Orient by creating or refining a pattern, and Write last_updated plus mex log entries when rationale matters.

Agent Memory Mode

mex setup --mode agent-memory creates a scaffold for persistent agents whose "project" is an operational environment rather than a code repo. It adds a HEARTBEAT.md contract and templates that frame mex as structured, task-routed memory:

• ROUTER.md tracks current operational state and routes the agent to the right memory files.
• context/ stores architecture, stack, conventions, setup, and decisions.
• patterns/ stores recurring runbooks.
• .mex/events/decisions.jsonl stores append-only notes and rationale via mex log.

mex heartbeat is intentionally lighter than mex check: it reads last_updated frontmatter and memory cleanup metadata, prints HEARTBEAT_OK when clean, and reports only when the agent needs to review stale context or memory files. Use mex watch --interval to run heartbeat repeatedly in a persistent-agent workspace.

Configuration

Optional settings live in .mex/config.json. Missing values fall back to defaults.

{
  "staleness": {
    "warnDays": 30,
    "errorDays": 90,
    "warnCommits": 50,
    "errorCommits": 200
  },
  "heartbeat": {
    "staleDays": 7,
    "memoryCleanupDays": 7,
    "dailyMemoryRetentionDays": 14
  },
  "watch": {
    "intervalMinutes": 30
  }
}

File Structure

your-project/
├── CLAUDE.md              ← auto-loaded by tool, points to .mex/
├── .mex/
│   ├── ROUTER.md          ← routing table, session bootstrap
│   ├── AGENTS.md          ← always-loaded anchor (~150 tokens)
│   ├── HEARTBEAT.md       ← agent-memory heartbeat contract (agent-memory mode)
│   ├── events/
│   │   └── decisions.jsonl   # append-only notes/decisions from mex log
│   ├── context/
│   │   ├── architecture.md   # how components connect
│   │   ├── stack.md           # technology choices and reasoning
│   │   ├── conven