Clawdbot is an open supply private AI assistant that you simply run by yourself {hardware}. It connects massive language fashions from suppliers resembling Anthropic and OpenAI to actual instruments resembling messaging apps, information, shell, browser and sensible residence gadgets, whereas preserving the orchestration layer beneath your management.
The attention-grabbing half will not be that Clawdbot chats. It’s that the challenge ships a concrete structure for native first brokers, and a typed workflow engine known as Lobster that turns mannequin calls into deterministic pipelines.
Structure: Gateway, Nodes and Abilities
On the heart of Clawdbot is the Gateway course of. The Gateway exposes a WebSocket management airplane on ws://127.0.0.1:18789 and an area HTTP interface for the management UI and net chat.
Your messages from WhatsApp, Telegram, Sign, Slack, Discord, iMessage and different channels are delivered to the Gateway. The Gateway decides which agent ought to deal with the message, which instruments it might name, and which mannequin supplier to make use of. It then sends the reply again over the identical channel.
The runtime is break up into a number of core ideas:
- Gateway: Routing, mannequin calls, device invocation, periods, presence and scheduling.
- Nodes: Processes that give Clawdbot entry to native assets resembling file system, browser automation, microphone, digicam or platform particular APIs on macOS, Home windows, Linux, iOS and Android.
- Channels: Integrations for chat techniques like WhatsApp, Telegram, Discord, Slack, Sign, Microsoft Groups, Matrix, Zalo and extra. These are configured as channel backends that connect to the Gateway.
- Abilities and plugins: Instruments that the agent can name, described in an ordinary
SKILL.mdformat and distributed by way of ClawdHub.
This separation allows you to run the Gateway on a 5 greenback digital server or a spare machine at residence, whereas preserving heavy mannequin compute on distant APIs or native mannequin backends when wanted.
Abilities and the SKILL.md customary
Clawdbot makes use of an open abilities format described in SKILL.md. A talent is outlined in Markdown with a small header and an ordered process. For instance, a deployment talent may specify steps resembling checking git standing, working exams and deploying solely after success.
---
title: deploy-production
description: Deploy the present department to manufacturing. Use solely after exams cross.
disable-model-invocation: true
---
1. Verify git standing guaranteeing clear working listing.
2. Run `npm check`
3. If exams cross, run `npm run deploy`
The Gateway reads these definitions and exposes them to brokers as instruments with express capabilities and security constraints. Abilities are printed to ClawdHub and might be put in or composed into bigger workflows.
Which means that operational runbooks can transfer from ad-hoc wiki pages into machine executable abilities, whereas nonetheless being auditable as textual content.
Lobster: Typed Workflow Runtime for Brokers
Lobster is the workflow runtime that powers Native Lobster and lots of superior Clawdbot automations. It’s described as a typed workflow shell that lets Clawdbot run multi step device sequences as a single deterministic operation with express approval gates.
As a substitute of getting the mannequin name many instruments in a loop, Lobster strikes orchestration right into a small area particular runtime:
- Pipelines are outlined as JSON or YAML, or as a compact shell like pipeline string.
- Steps alternate typed JSON information, not unstructured textual content.
- The runtime enforces timeouts, output limits and sandbox insurance policies.
- Workflows can pause on uncomfortable side effects and resume later with a
resumeToken.
A easy inbox triage workflow seems like this:
title: inbox-triage
steps:
- id: accumulate
command: inbox record --json
- id: categorize
command: inbox categorize --json
stdin: $accumulate.stdout
- id: approve
command: inbox apply --approve
stdin: $categorize.stdout
approval: required
- id: execute
command: inbox apply --execute
stdin: $categorize.stdout
situation: $approve.authorized
Clawdbot treats this file as a talent. If you ask it to scrub your inbox, it calls one Lobster pipeline as an alternative of improvising many device calls. The mannequin decides when to run the pipeline and with which parameters, however the pipeline itself stays deterministic and auditable.
Native Lobster is the reference agent that makes use of Lobster to drive native workflows and is described in protection as an open supply agent that redefines private AI by pairing native first workflows with proactive conduct.
Proactive native first conduct
A key cause Clawdbot is trending and visual on X and in developer communities is that it behaves like an operator, not only a chat window.
As a result of the Gateway can run scheduled jobs and observe state throughout periods, widespread patterns embrace:
- Each day briefings that summarize calendars, duties and necessary mail.
- Periodic recaps resembling weekly shipped work summaries.
- Displays that look ahead to circumstances, then message you first in your most popular channel.
- File and repository automations that run regionally however are triggered by pure language.
All of this runs with routing and gear coverage in your machine or server. Mannequin calls nonetheless go to suppliers like Anthropic, OpenAI, Google, xAI or native backends, however the assistant mind, reminiscence and integrations are beneath your management.
Set up and developer workflow
The challenge supplies a one line installer that fetches a script from clawd.bot and bootstraps Node, the Gateway and core elements. For extra management, you may set up through npm or clone the TypeScript repository and construct with pnpm.
Typical steps:
curl -fsSL https://clawd.bot/set up.sh | bash
# or
npm i -g clawdbot
clawdbot onboard
After onboarding you join a channel resembling Telegram or WhatsApp, select a mannequin supplier and allow abilities. From there you may write your individual SKILL.md information, construct Lobster workflows and expose them by way of chat, net chat or the macOS companion utility.
Some Examples
Michal Sutter is a knowledge science skilled with a Grasp of Science in Knowledge Science from the College of Padova. With a strong basis in statistical evaluation, machine studying, and information engineering, Michal excels at remodeling advanced datasets into actionable insights.
