LobsterAI

What does this agent do, and when should you use it?

LobsterAI is an Electron desktop application maintained by NetEase Youdao for long-running work across local files, documents, spreadsheets, slides, browser workflows, and project workspaces. Its Cowork session layer owns local persistence, permissions, UI state, artifacts, agents, memory, and instant-messaging bindings, while OpenClaw provides the underlying execution runtime and gateway. The React renderer exposes sessions, agents, skills, MCP, scheduled tasks, and IM settings; the Electron main process handles IPC, SQLite, authentication, logging, and runtime management. The app can preview generated HTML, SVG, images, video, Mermaid diagrams, code, Markdown, text, and office-document artifacts. It fits users or teams that want an agent to operate on their actual desktop environment with approval for sensitive actions.

A user submits work in a Cowork session, where the application streams progress and tool output while retaining session history; it requests approval for sensitive file operations, terminal commands, and network access. openclawConfigSync renders locally configured providers, models, Agents, IM bindings, skills, MCP servers, and workspace instructions into OpenClaw configuration. openclawEngineManager manages the gateway process, runtime state, ports, logs, restart, and repair, while openclawRuntimeAdapter translates gateway events into Cowork stream events. The application stores sessions, messages, configuration, agents, and memory metadata in SQLite, and retains workspace memory in files including MEMORY.md, USER.md, SOUL.md, and daily notes. It also manages scheduled work and can connect the desktop agent to WeChat, WeCom, DingTalk, Feishu/Lark, QQ, Telegram, Discord, email, and other listed IM channels.

1. A small business still tracking purchases and sales in Excel can ask it to build a local inventory system that calculates stock and profit and opens in a browser.
2. An operations analyst working with a local product-growth.xlsx file can produce a visual dashboard and a summary of growth drivers.
3. A business user preparing an AI-agent market briefing can request research and a presentation from the findings.
4. A marketer who checks an ads dashboard each morning can automate browser checks and receive a summary of spend or conversion anomalies.
5. A recruiter screening resumes in a local folder can turn them into a screening sheet and shortlist candidates against a job description.
6. A user away from their computer can send work to a specifically bound desktop agent through a supported IM channel.

How do you install or deploy this agent?

Desktop installers for macOS and Windows are available through the official site or GitHub Releases. Running from source requires Node.js >=24.15.0 <25 and npm:

git clone https://github.com/netease-youdao/LobsterAI.git
cd LobsterAI
npm install

For the first development run, use: npm run electron:dev:openclaw. Once the pinned OpenClaw runtime exists locally, use: npm run electron:dev. The supplied material does not document model-provider credential setup or the credentials required for a first working conversation.

How do you use this agent?

After launch, enter a task concerning local projects, files, or browser work in a Cowork session, and approve sensitive file, terminal, or network actions when prompted. Create specialized Agents in the agent settings with their own identity, model choice, skills, working directory, enabled state, and IM binding; use MCP settings to add external MCP servers, and create recurring work through conversation or the scheduled-task UI. In development mode, the renderer server runs at http://localhost:5175.

What are this agent's strengths and limitations?

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

How does FollowAgents rate this agent?

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

1. 2026.11.6 LobsterAI 2026.11.6 2026-11-06
   Release notes excerpt

   2026.11.2 A release focused on reliability: chat streams now survive mid-reply drops, oversized contexts recover with visible compaction progress, the image pipeline is cheaper and less chatty, and installers ship a lot less dead weight. Highlights 1. Model streams reconnect automatically when they drop mid-reply instead of leaving the message truncated (#2974). 2. Oversized conversations now recover instead of failing, with compaction progress surfaced in the UI (#2982, #3014, #2988). …

   View on GitHub ↗
2. 2026.10.30 LobsterAI 2026.10.30 2026-10-31
   Release notes excerpt

   2026.10.30 Highlights - Image Studio lands — a new image creation surface with close-up erase-and-blend, per-conversation media model selection, and a fixed sharing path for generated images - Conversation polish — large pastes collapse into cards, and history keeps loading until the viewport is full - Account & settings — one saved API key per decision-model provider; redesigned IM settings with WeChat DMs always admitted - Faster startup — startup migrations no longer rerun on every launch, and state databases are prewarmed ✨ New Features …

   View on GitHub ↗
3. 2026.10.23 LobsterAI 2026.10.23 2026-10-23
   Release notes excerpt

   This release brings image editing into your conversations, makes remote tools easier to connect, and gives you clearer visibility into usage. It also improves startup reliability, browser tasks, and account recovery. ✨ Highlights Edit images without leaving your conversation Annotate images with drawings, arrows, shapes, and text, or select an area and describe what you want to change. With a compatible image model, you can remove backgrounds, erase objects, and expand images to a new aspect ratio. …

   View on GitHub ↗

FAQ