openclaw-memory-vectorize: Instructions file for Codex

AGENTS.md

For AI agents (Claude Code, Cursor, Copilot, etc.): This file tells you how to work with this repo.

---

Quick Setup (Execute These Commands)

# 1. Install dependencies
cd worker && npm install && cd ..

# 2. Create Vectorize index (skip if exists)
npx wrangler vectorize create agent-memories --dimensions=768 --metric=cosine
npx wrangler vectorize create-metadata-index agent-memories --property-name=agent --type=string
npx wrangler vectorize create-metadata-index agent-memories --property-name=type --type=string

# 3. Deploy worker
cd worker && npx wrangler deploy && cd ..

# 4. Install plugin (for OpenClaw users)
mkdir -p ~/.openclaw/extensions/memory-vectorize
cp plugin/index.ts ~/.openclaw/extensions/memory-vectorize/
cp plugin/openclaw.plugin.json ~/.openclaw/extensions/memory-vectorize/

# 5. Install memory provider (for Hermes users)
mkdir -p "$HERMES_HOME/plugins/openclaw-memory-vectorize"
cp __init__.py plugin.yaml "$HERMES_HOME/plugins/openclaw-memory-vectorize/"

---

Project Overview

OpenClaw and Hermes plugin for persistent agent memory using Cloudflare Vectorize + Workers AI.

What it does:

• Stores memories as vector embeddings
• Auto-recalls relevant context before agent responses
• Auto-captures decisions, corrections, preferences after responses
• Registers as the openclaw-memory-vectorize Hermes memory provider

---

Structure

├── worker/                    # Cloudflare Worker (API)
│   ├── src/index.ts          # ← MAIN FILE: All endpoints
│   ├── wrangler.jsonc        # Cloudflare config
│   └── package.json
├── plugin/                    # OpenClaw integration
│   ├── index.ts              # ← MAIN FILE: Lifecycle hooks
│   └── openclaw.plugin.json  # Plugin manifest
├── scripts/                   # CLI
│   └── memory_cli.py          # search / index / index-all / health / stats
├── README.md                  # User documentation
└── AGENTS.md                  # This file

---

Key Files to Modify