betaMinds Connected, Tasks Done

NearWork: turn every conversation into a real result

An AI assistant for everyone — chat, code, tools and models, organised into one clear, quiet entry point that's always ready.

Read the docs →
75
Built-in tools
Any model
Bring your own
Local-first
Your data
NearWork · Meeting notesDone
User

Turn this meeting recording into key points and action items.

Read file
meeting-0930.mp3 · 4,820 chars transcribed
NearWork

Done. ① Set the Q3 growth target; ② marketing to ship the campaign this week; ③ 3 action items assigned by owner.

Add more, or have NearWork draft the meeting notesSend

Product Demo

Why NearWork

Universal Model Support

Universal Model Support

Compatible with OpenAI, Anthropic & Gemini protocols. Connect any model on the market. 7 purpose-built model slots with automatic routing.

60+ Built-in Tools

60+ Built-in Tools

Code editing, file ops, Git, SSH, Office docs, PDF & OCR — covering the full dev workflow.

Computer Use

Computer Use

AI sees the screen and drives the mouse & keyboard to operate desktop apps for you.

23 Built-in Skills

23 Built-in Skills

Code gen & review, bug fixing, docs, data analysis, translation — ready to use.

Extensible & Parallel

Extensible & Parallel

Connect any external tool via MCP; up to 16 concurrent sub-agents.

Voice Interaction

Voice Interaction

Continuous voice conversations. Hands-free, just speak to get work done.

Phone & Multi-device

Phone & Multi-device

Assign work straight from Feishu / WeCom; Desktop · Web console · CLI · VS Code share one engine, with unattended scheduled tasks.

Local-First Privacy

Local-First Privacy

Encrypted API keys, 4-tier permissions, dangerous ops auto-blocked. Your files and keys never leave your machine.

Team Collaboration

Team Collaboration

A multi-agent team: a leader plans while each member carries its own role, skills and MCP servers — work is split, run in parallel and summarised.

Everywhere You Work

Desktop App

Desktop App

Windows / Mac / Linux, full experience

CLI Tool

CLI Tool

Dev-first, pipe & script integration

VS Code Extension

VS Code Extension

Inline completions, review, refactor

HTTP Server

HTTP Server

Remote engine, team & API access

Desktop apps

Download & Get Started

NearWork Assistant · Windows / Linux / macOS desktop apps

Your system
Windows Desktop App
Windows 10/11 · x64 · Installer ~100 MB
Installer is unavailable right now — please try again later
Linux Desktop App
Ubuntu / Debian / Fedora · x64 · deb / rpm
Installer is unavailable right now — please try again later
macOS Desktop App
macOS 11+ · Apple Silicon (M series)
macOS is coming soon

Or install CLI via npm

$ npm install -g @lingxi-agent/core
$ lingxi

Requires Node.js 22+

Frequently asked questions

What people ask most before installing: which models work, whether you need your own API key, and where your data lives.

What is NearWork?

NearWork is a multi-model desktop AI agent, not just a chat window: it reads and writes local files, runs commands, fetches web pages and calls tools and skills, turning a one-line request into a finished result.

Which models does NearWork support?

Over the OpenAI, Anthropic and Gemini API protocols, NearWork connects to 16 model providers, including DeepSeek, Qwen, Kimi, Zhipu, Doubao, MiniMax, ERNIE, Hunyuan, StepFun, OpenAI, Anthropic, Gemini, xAI, Groq and Mistral.

Do I need my own API key?

No. You can use the official model credits, or enter your own API key in settings, in which case requests go straight to the provider you chose.

Where is my data stored?

Configuration, sessions, skills, the knowledge base and memory live in a local data directory (defaults to ~/.LingXi, overridable with the LINGXI_HOME environment variable). Only the inference requests sent to your chosen provider leave the machine, and API keys are encrypted locally.

Is NearWork free?

Yes, the free plan is available on sign-up and includes official model credits; see the pricing page for more credits and team features.

Does NearWork support MCP?

Yes. Any MCP server can be added through mcp.json, with user-level and project-level configuration, plus a plugin marketplace.

Scan to reach us on WeChat

NearWork WeChat QR code

Scan the code to add us on WeChat