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.
npx agentmods add instructions/atlas-os1/openclaw-memory-vectorize/agents-mdgit clone --depth 1 https://github.com/Atlas-Os1/openclaw-memory-vectorizeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/atlas-os1/openclaw-memory-vectorize/agents-md)<a href="https://agentmods.dev/instructions/atlas-os1/openclaw-memory-vectorize/agents-md"><img src="https://agentmods.dev/badge/instructions/atlas-os1/openclaw-memory-vectorize/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01081 | $0.01081 |
| Opus 5 | $0.00541 | $0.00541 |
| Sonnet 5 | $0.00216 | $0.00216 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
openclaw-memory-vectorize AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8787/health How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
For AI agents (Claude Code, Cursor, Copilot, etc.): This file tells you how to work with this repo.
Quick Setup (Execute These Commands)
# 1. Install dependencies
cd worker && npm install && cd ..
# 2. Create Vectorize index (skip if exists)
npx wrangler vectorize create agent-memories --dimensions=768 --metric=cosine
npx wrangler vectorize create-metadata-index agent-memories --property-name=agent --type=string
npx wrangler vectorize create-metadata-index agent-memories --property-name=type --type=string
# 3. Deploy worker
cd worker && npx wrangler deploy && cd ..
# 4. Install plugin (for OpenClaw users)
mkdir -p ~/.openclaw/extensions/memory-vectorize
cp plugin/index.ts ~/.openclaw/extensions/memory-vectorize/
cp plugin/openclaw.plugin.json ~/.openclaw/extensions/memory-vectorize/
# 5. Install memory provider (for Hermes users)
mkdir -p "$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-vectorizeHermes 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
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.
- 4d ago First seen · 152 lines · 1,081 tokens per session scan A 34a46b8a6143
openclaw-memory-vectorize AGENTS.md is an instructions file published in the GitHub repository Atlas-Os1/openclaw-memory-vectorize (2 stars, last pushed 20d ago), licensed MIT. It adds 1,081 tokens to every session, about $0.0054 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
memsearch CLAUDE.md
Claude Code instructions for zilliztech/memsearch, covering claude.md, build & test commands, install in development mode, run a single test file and run a specific test.
palaia AGENTS.md
AGENTS.md instructions for byte5ai/palaia, covering agent instructions, git workflow, pull requests, project and pre-push hook.
palaia CLAUDE.md
Claude Code instructions for byte5ai/palaia: All agent rules for this repository live in AGENTS.md — git workflow, the strict v2/v3 track separation, v3 project conventions, and PR requirements.
signetai CLAUDE.md
Claude Code instructions for Signet-AI/signetai, a project described as: Sync and store memories, shared identity files (AGENTS.md, CLAUDE.md), session transcripts, institutional knowledge, and secrets between all of your favorite harnesses and models.
CloudMind AGENTS.md
AGENTS.md instructions for evepupil/CloudMind, covering cloudmind agents.md, 项目定位, 架构方向升级（2026-06-05）：个人私有化 ai 记忆层, 当前产品定义 and mvp 原则.
claw-kit CLAUDE.md
Instructions for tstockham96/claw-kit, covering claw kit, what this is, project structure, quick start and memory system.