openclaw

openclaw is an agent for coding agents from zorost/AI-Engineering-Lab. It costs 0 tokens per session (4,115 once invoked), scanned C, original, MIT.

A practical guide to OpenClaw, an open-source personal AI assistant that runs on your devices and connects to messaging channels.

In plain words
What is it for?
It helps install and run OpenClaw, connect it to a local AI model, configure messaging channels, and connect it to an MCP server.
Why use it?
It explains the assistant’s setup and architecture for people who want to operate it themselves, while flagging details that may change.

Agent

Install

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.

agentmods
npx agentmods add agents/zorost/ai-engineering-lab/openclaw
Clone the repo
git clone --depth 1 https://github.com/zorost/AI-Engineering-Lab

Wrote 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.

agentmods badge for openclaw

README.md
[![agentmods](https://agentmods.dev/badge/agents/zorost/ai-engineering-lab/openclaw.svg)](https://agentmods.dev/agents/zorost/ai-engineering-lab/openclaw)
Your own site
<a href="https://agentmods.dev/agents/zorost/ai-engineering-lab/openclaw"><img src="https://agentmods.dev/badge/agents/zorost/ai-engineering-lab/openclaw.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,115 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.04115
Opus 5 $0.00000 $0.02057
Sonnet 5 $0.00000 $0.00823
Haiku 4.5 $0.00000 $0.00411

Measured 3d ago against content hash 600607d7afb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

openclaw scanned grade C with 2 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 3d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://openclaw.ai/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://openclaw.ai/install.sh | bash
reference/agents/openclaw.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenClaw: Practical Guide

Part of AI Engineering Lab · Developed by Zorost Intelligence AI Lab · zorost.com

OpenClaw is the personal-AI-assistant track of Week 17: an open-source assistant that runs on your devices and meets you in the messaging channels you already use. This guide walks through what it is, how it's architected, how to install and run it, how to point it at a local model, and how to wire it to your Week-16 MCP server.

Note on fast-moving facts. OpenClaw renamed itself several times, and its config keys and channel list change frequently. Everything marked "verify against live docs" below should be checked at docs.openclaw.ai before you rely on it.


1. What OpenClaw is

OpenClaw is an open-source personal AI assistant that runs on your own devices and meets you in the messaging channels you already use, WhatsApp, Telegram, Discord, Slack, Signal, iMessage, and a built-in WebChat. It is designed for a single operator, and it connects models, tools, messaging channels, and optional companion apps through one Gateway (OpenClaw README).

Key facts to keep straight:

  • License: MIT.
  • Creator: originally created by Peter Steinberger (steipete) and a large community; now developed in the open by the OpenClaw Foundation, a non-profit.
  • Mascot: "Molty," a space lobster.
  • Repo: github.com/openclaw/openclaw · Docs: docs.openclaw.ai · Site: openclaw.ai.

1.1 The naming history (get it right)

The project was renamed several times, and the history matters because older tutorials still use the old names:

  1. Clawdbot: the original viral project (late 2025).
  2. Moltbot: renamed in January 2026; the "Molty the space lobster" mascot dates from here.
  3. OpenClaw: the current name (a third rename, driven in part by trademark / impersonation pressure and crypto-scam squatting of earlier names).

(TechCrunch naming history)

Read the full file on GitHub · 361 lines

Changes

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.

  1. 3d ago First seen · 361 lines · 0 tokens per session scan C 600607d7afb2

Subscribe to this mod's changes

openclaw is an agent published in the GitHub repository zorost/AI-Engineering-Lab (304 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,115 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.