Clawdbot is an open supply private AI assistant that you simply run by yourself {hardware}. It connects giant language fashions from suppliers akin to Anthropic and OpenAI to actual instruments akin to messaging apps, recordsdata, shell, browser and good dwelling units, whereas protecting the orchestration layer below your management.
The attention-grabbing half is just not that Clawdbot chats. It’s that the mission ships a concrete structure for native first brokers, and a typed workflow engine referred to as Lobster that turns mannequin calls into deterministic pipelines.
Structure: Gateway, Nodes and Expertise
On the middle of Clawdbot is the Gateway course of. The Gateway exposes a WebSocket management aircraft on ws://127.0.0.1:18789 and an area HTTP interface for the management UI and internet 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 could name, and which mannequin supplier to make use of. It then sends the reply again over the identical channel.
The runtime is cut up into a couple of core ideas:
- Gateway: Routing, mannequin calls, instrument invocation, periods, presence and scheduling.
- Nodes: Processes that give Clawdbot entry to native sources akin to file system, browser automation, microphone, digital camera or platform particular APIs on macOS, Home windows, Linux, iOS and Android.
- Channels: Integrations for chat methods like WhatsApp, Telegram, Discord, Slack, Sign, Microsoft Groups, Matrix, Zalo and extra. These are configured as channel backends that connect to the Gateway.
- Expertise and plugins: Instruments that the agent can name, described in a typical
SKILL.mdformat and distributed by way of ClawdHub.
This separation permits you to run the Gateway on a 5 greenback digital server or a spare machine at dwelling, whereas protecting heavy mannequin compute on distant APIs or native mannequin backends when wanted.
Expertise and the SKILL.md commonplace
Clawdbot makes use of an open expertise format described in SKILL.md. A talent is outlined in Markdown with a small header and an ordered process. For instance, a deployment talent would possibly specify steps akin to 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. Test 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 specific capabilities and security constraints. Expertise are revealed to ClawdHub and could be put in or composed into bigger workflows.
Which means that operational runbooks can transfer from ad-hoc wiki pages into machine executable expertise, whereas nonetheless being auditable as textual content.
Lobster: Typed Workflow Runtime for Brokers
Lobster is the workflow runtime that powers Native Lobster and plenty of superior Clawdbot automations. It’s described as a typed workflow shell that lets Clawdbot run multi step instrument sequences as a single deterministic operation with specific approval gates.
As an alternative 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 negative effects and resume later with a
resumeToken.
A easy inbox triage workflow appears to be like like this:
title: inbox-triage
steps:
- id: acquire
command: inbox record --json
- id: categorize
command: inbox categorize --json
stdin: $acquire.stdout
- id: approve
command: inbox apply --approve
stdin: $categorize.stdout
approval: required
- id: execute
command: inbox apply --execute
stdin: $categorize.stdout
situation: $approve.permitted
Clawdbot treats this file as a talent. Whenever you ask it to wash your inbox, it calls one Lobster pipeline as an alternative of improvising many instrument 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 habits.
Proactive native first habits
A key purpose 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 essential mail.
- Periodic recaps akin to weekly shipped work summaries.
- Displays that look ahead to circumstances, then message you first in your most well-liked 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 below your management.
Set up and developer workflow
The mission gives 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 akin to Telegram or WhatsApp, select a mannequin supplier and allow expertise. From there you may write your personal SKILL.md recordsdata, construct Lobster workflows and expose them by way of chat, internet chat or the macOS companion software.
Some Examples
