After setup, try: “One thing I want to move forward this week is ____. Help me find the smallest credible next step.”

Why try xopc

  • Start before it is organized. Drop in text, voice, files, links, or a thought you cannot explain clearly yet.
  • Stop repeating yourself. Sessions, projects, tasks, and correctable user understanding keep the context that matters.
  • Move beyond advice. xopc can use tools, run workflows, verify results, and continue the work later.
  • Stay in control. It is local-first, sources are authorized separately, and high-impact actions such as sending or deleting require confirmation.

Keep what matters moving. xopc keeps context, the next action, evidence, and follow-up together, so important work does not disappear when a chat ends.

xopc works from desktop, web, terminal, mobile, Telegram, WeChat, and Feishu/Lark, with your choice of cloud or local models.

For the full product philosophy, trust model, and roadmap, read Product philosophy.

Get started

Easiest start: desktop app

For most users, the desktop app is the easiest way to start: install the app, finish model setup in the UI, then chat in the built-in console. It starts the local gateway for you.

  1. Open xopc.ai and choose macOS, Windows, or Linux.
  2. Open xopc and complete model setup.
  3. Start chatting.

See Desktop app for install notes, first-run guidance, and build-from-source commands.

One-liner (30-second start — recommended)

Linux, macOS, WSL2, Termux

curl -fsSL https://xopc.ai/install.sh | bash

Windows (native, PowerShell)

Heads up: Native Windows runs xopc without WSL — CLI, gateway, TUI, and tools all work natively. Prefer WSL2? Use the bash one-liner above there too.

iex (irm https://xopc.ai/install.ps1)

The installer detects your OS, installs Node.js ≥ 22 when needed, and installs @xopcai/xopc. China mirror: add --cn (bash) or -Cn (PowerShell), or pass --registry https://registry.npmmirror.com.

Then chat immediately:

xopc onboard --quick
xopc                    # opens the local TUI

npm (already have Node.js 22+)

npm install -g @xopcai/xopc

Or with pnpm: pnpm add -g @xopcai/xopc · China mirror: npm install -g @xopcai/xopc --registry=https://registry.npmmirror.com

Large optional runtimes are installed only when you enable the related feature:

npm install -g @huggingface/[email protected] [email protected]
npm install -g @composio/[email protected] @composio/[email protected]
npm install -g @larksuiteoapi/[email protected] [email protected]

Use the same command without -g when xopc is installed as a project dependency.

More commands

xopc agent -i                               # interactive CLI
xopc agent -m "Summarize the last 5 commits"  # one-shot
xopc gateway                                # web server + React console
xopc gateway service install                # OS service

From source (installer or pnpm workspace):

# installer — clone, build, and add ~/.local/bin/xopc wrapper
curl -fsSL https://xopc.ai/install.sh | bash -s -- --install-method git

# or manual checkout
git clone https://github.com/xopcai/xopc.git && cd xopc
corepack enable && pnpm install && pnpm run build
pnpm exec xopc onboard

Windows git install: & ([scriptblock]::Create((irm https://xopc.ai/install.ps1))) -InstallMethod git

Requirements: Node.js ≥ 22 (the one-liner handles this). Use pnpm when hacking from a git clone. More install options on xopc.ai and Getting started.

Where to chat

Surface How Best for
Desktop app Download from xopc.ai Easiest start: native app + embedded gateway console
TUI xopc or xopc tui (remote: xopc tui --url …) Full keyboard, streaming, fastest terminal path
CLI xopc agent -i / xopc agent -m "…" Scripts and minimal TTY
Web xopc gateway → open console URL Chat, settings, logs in the browser
Mobile mobile app + QR gateway pairing (mobile app, remote access) Chat, record notes, and capture ideas from iOS/Android while the agent keeps running on your computer
Messengers channels.* + gateway Telegram, WeChat, Feishu/Lark

Channels

Configure under channels.* in ~/.xopc/xopc.json. IM bots need a running gateway; WeChat login runs on the gateway host.

Channel Config Notes
Telegram channels.telegram Multi-account, streaming, policies
WeChat channels.weixin QR login on gateway host
Feishu / Lark channels.feishu Bot / webhook per docs

Full reference: Channels · Configuration.

Extensions & skills

xopc skills install <name>       # SKILL.md domains
xopc extensions install store:<id>  # or npm:<package> / ./local-directory
xopc extensions dev ./my-extension

Guides: Extensions · Skills. Gateway UI extensions: @xopcai/xopc/extension-ui-sdk (packages/extension-ui-sdk/).

Configuration

Default: ~/.xopc/xopc.json. A minimal skeleton:

{
  "providers": { "deepseek": "${DEEPSEEK_API_KEY}" },
  "agents": { "default": "main", "list": [{ "id": "main", "models": { "roles": { "deep": { "model": "deepseek/deepseek-v4-flash" } } } }] }
}

Full reference: Configuration. Add channels.* for IM, or browser tools (Playwright Chromium) when needed.

Documentation

Guide Description
Getting started Install, onboard, first chat
The Continuous Work Model How state, execution, and triggers form resumable, inspectable work loops
Projects, Tasks, and Notes Keep long-running work in one verified Task model with optional shared project context
Configuration xopc.json reference
CLI Commands and flags
Channels Telegram, WeChat, Feishu
Architecture How pieces fit together
Workflows Fan-out subagents, board UI, scripts

Also: Tools · Mobile app · Voice · Remote access

FAQ

Is xopc a hosted service? — No. xopc runs on your machine, with configuration and state stored under ~/.xopc/ by default. You can self-host the gateway for access from other devices.

Does local-first mean data never leaves my computer? — Not necessarily. If you select a cloud model, conversation content and context relevant to the request are sent to that model provider. Use a local model and review source and tool permissions for work that must remain on-device.

Does xopc remember everything about me automatically? — No. User understanding can be reviewed, confirmed, corrected, and deleted, and an unconfirmed inference should not become an authoritative fact. Passwords, keys, and other highly sensitive information do not belong in the memory system.

Do I need a paid cloud model? — No. Bring your own keys, or use local models (Ollama, LM Studio, vLLM).

What is the fastest way to try it? — Desktop app for GUI users, or xopc onboard --quick && xopc for terminal.

How is this different from another chat UI? — Chat is only one surface. xopc preserves understanding, long-term goals, projects, tasks, decisions, and run history so the same assistant can continue working across time and surfaces.

Can I use it from my phone or messengers? — Yes. Pair the mobile app by QR code, or configure Telegram, WeChat, or Feishu/Lark via the gateway.

Have a question? — Ask on GitHub Discussions.

Security

xopc handles personal context and may be given execution tools, so capability boundaries matter as much as model choice:

  • enable only the data sources, tools, and channels you currently need;
  • before using a cloud model, understand what context may be sent to the provider;
  • treat all inbound messenger content as untrusted input and prefer pairing or allowlist for DMs;
  • keep gateway bind addresses, access tokens, and API keys private;
  • preserve human confirmation for sending, deleting, purchasing, and other high-impact actions.

See User understanding and privacy, channel security, and the configuration reference.

Contributing

pnpm install && pnpm run dev    # CLI via tsx
pnpm run dev:gateway            # dev gateway uses ~/.xopc-dev + info logs
pnpm run build && pnpm test && pnpm run lint

AGENTS.md · CONTRIBUTING.md

Issues: Bug report · Feature request · Q&A Discussions · Security advisory (not public issues)

Tech stack: TypeScript, Node.js ≥ 22, pnpm workspace. Built-in LLM layer via @earendil-works/pi-ai, React gateway console, Electron desktop.

Credits