LobsterAI
Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your pho...
Source#
- Repository: netease-youdao/LobsterAI
- Last source update: 2026-06-21
- Last verified: 2026-06-21
Tags#
Integration notes#
Repository is focused on tool/server interoperability; wrap in bounded worker contracts for production use.
worker.md example#
Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.
---
id: lobsterai-repo-derived-worker
name: LobsterAI Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/lobsterai/
source_repository: https://github.com/netease-youdao/LobsterAI
repository_default_branch: main
repository_language: TypeScript
repository_license: MIT
repository_updated_at: 2026-06-21
worker_mode: workflow-automation-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-06-21
tags:
- agent
- ai-agent
- ai-assistant
- automation
- autonomous-agents
- chatbot
---
# LobsterAI Repo-Derived Worker
## Repo-derived summary
- Registry summary: Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your pho...
- Repository description: Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram.
- Stars (snapshot): 5,310
- Primary language: TypeScript
- Worker mode classification: workflow-automation-worker
## Extracted from
- https://github.com/netease-youdao/LobsterAI
- https://github.com/netease-youdao/LobsterAI/blob/main/README.md
- https://wp.m.163.com/163/html/bee/lobsterai_guide/index.html
- https://api.star-history.com/svg?repos=netease-youdao/LobsterAI&type=date&legend=top-left
## Evidence notes (from repository text)
- README summary paragraph: A 24/7 all-scenario office assistant Agent that gets real work done — built by NetEase Youdao
- # LobsterAI — All-Scenario Office Assistant Agent
- A 24/7 all-scenario office assistant Agent that gets real work done — built by NetEase Youdao
- The first open-source, desktop-grade Agent from a major Chinese tech company — publicly praised by OpenClaw's founder.
- - **🖥️ Desktop-grade Agent** — Connects to your files, terminal, browser, and local projects, working directly inside your real environment instead of a sandboxed chat box
- - **🧩 OpenClaw ecosystem** — Built on the open-source OpenClaw Agent framework, with continuous access to new Skills, tools, MCP servers, and models
## Installation hints found in README
- `npm install` → `build` → `ui:build` → pack to asar | Only when version changed |`
## worker.md contract (derived starter)
Purpose: Execute one automation workflow step in a bounded worker run.
### Input schema
```json
{
"type": "object",
"additionalProperties": false,
"required": [
"run_id",
"trigger",
"step"
],
"properties": {
"run_id": {
"type": "string"
},
"trigger": {
"type": "object"
},
"step": {
"type": "string"
}
}
}
```
### Output schema
```json
{
"type": "object",
"additionalProperties": false,
"required": [
"run_id",
"step",
"status",
"artifacts"
],
"properties": {
"run_id": {
"type": "string"
},
"step": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"ok",
"retryable_error",
"invalid_request",
"invalid_output"
]
},
"artifacts": {
"type": "array"
}
}
}
```
### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: run_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use
## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.
How to use#
- Save this as a worker spec file (for example:
lobsterai-my-task.worker.md). - Replace the input/output schemas and purpose with your real bounded task.
- Enforce schema validation + timeout + retry policy in your runtime before production use.
Citation#
Reference URL: https://worker.md/registry/lobsterai/
Source URL: https://github.com/netease-youdao/LobsterAI