English | 简体中文

xopc

Goal Loop OS. Long-term AI in one loop.
A local-first AI assistant that keeps long-term goals moving across terminal, web, desktop, mobile app, and messengers.

xopc.ai · GitHub · Documentation · Get started · Releases

---

Built for

• Long-running projects — keep direction, next actions, feedback, and recalibration in one loop instead of losing context between chats.
• One-person companies and solo builders — use the same assistant from CLI, TUI, Web, Desktop, Telegram, WeChat, and Feishu/Lark.
• Local-first AI workflows — bring your own keys, mix cloud/local models, add skills/extensions, and keep data under ~/.xopc/.

---

Get started

Try in 3 minutes

curl -fsSL https://xopc.ai/install.sh | bash
xopc onboard --quick
xopc tui --local

This path starts the embedded terminal UI: no gateway, desktop app, or messenger setup required.

One-liner (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.

Run this in PowerShell:

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.

30-second start: this is the homepage-recommended path, including Node setup on macOS, Linux, and Windows.

Onboard & chat

xopc onboard          # faster: xopc onboard --quick
xopc tui --local

New here? Start with xopc tui --local (embedded agent, no gateway). Run xopc gateway when you want the web console or messengers (Telegram, WeChat, Feishu).

If the first run works for you, please star the repo so others can discover it.

npm (already have Node.js 22+)

npm install -g @xopcai/xopc

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

More commands

xopc agent -i                              # classic interactive CLI
xopc agent -m "Summarize the last 5 commits" # one-shot

xopc init                                  # full ~/.xopc state tree (first install / repair)
xopc gateway                               # local web server + React console (URL in logs)
xopc gateway service install               # OS service; xopc gateway stop | status | logs
xopc profile list                          # optional isolated state profiles

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.

---

Why xopc

• 🔁 Goal loops, not one-shot chats — keep long-term direction, action, and feedback moving together.

• 🏠 Your machine — Data and config under ~/.xopc/. No mandatory cloud or surprise bills.

• 🔑 Bring your own keys — OpenAI, Anthropic, Google, DeepSeek, Ollama, LM Studio, vLLM, and 20+ providers. Mix cloud and local; switch catalog models in one config line. See Models.

• 📱 One brain, every screen — Same assistant in terminal, browser, desktop, mobile app, and IM. No sync layer — one system.

• 🧩 Grows with you — xopc skills install · xopc extensions install for tools, channels, and UI panels; multi-agent routing per context.

• ⏰ Proactive — Cron for scheduled summaries and reminders; workflows for fan-out subagent tasks; multi-agent routing with isolated workspaces, tools, and prompts.

---

Where to chat

Surface	How	Best for
TUI	xopc tui --local (or xopc tui --url …)	Full keyboard, streaming, lowest friction to try
CLI	xopc agent -i / xopc agent -m "…"	Scripts and minimal TTY
Web	xopc gateway → open console URL	Chat, settings, logs in the browser
Desktop	GitHub Releases or pnpm run electron:build	Native app (macOS, Windows, Linux)
Mobile	xopc-app + gateway pairing (mobile app, remote access)	Continue your loop on iOS/Android
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 <pkg>    # tools, channels, UI panels
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.

{
  "agents": {
    "defaults": {
      "model": "deepseek/deepseek-chat",
      "max_tokens": 8192
    }
  },
  "providers": {
    "deepseek": "${DEEPSEEK_API_KEY}",
    "openai": "${OPENAI_API_KEY}"
  }
}

Add channels.telegram, channels.weixin, or channels.feishu when you need IM — see configuration.

Optional tools (e.g. browser) stay off until enabled; use Playwright Chromium if you turn on browser tools.

---

Documentation

Guide	Description
Getting started	Install, onboard, first chat
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. Config, workspace files, credentials, and local state live under ~/.xopc/ by default.

Do I need a paid cloud model?
No. Bring your own keys for cloud providers, or use local/model-server options such as Ollama, LM Studio, and vLLM.

What is the fastest way to try it?
Use xopc onboard --quick and xopc tui --local. That path avoids gateway, desktop, and messenger setup.

How is this different from another chat UI?
xopc is organized around goal loops: direction, next action, feedback, and recalibration across multiple surfaces.

Can I use it from my phone or messengers?
Yes. Start with local TUI first; when ready, run the gateway and use xopc-app on iOS/Android, or configure Telegram, WeChat, or Feishu/Lark.

If this answers your concerns, please star xopc so more developers can find it.

---

Desktop app

1. Download from GitHub Releases — macOS .dmg, Windows xopc-<version>-x64.exe or xopc-<version>-arm64.exe, Linux .AppImage / .deb.
2. Or use xopc gateway + the npm CLI until a build exists for your OS.

Build from source: pnpm install && pnpm run electron:build → dist/release/

---

Security

Treat inbound IM messages as untrusted. Prefer pairing or allowlist for DMs. Keep gateway bind addresses and tokens secret — Channels.

---

Contributing

pnpm install && pnpm run dev    # CLI via tsx
pnpm run build && pnpm test && pnpm run lint

AGENTS.md · CONTRIBUTING.md

Issues: bug · feature · Q&A Discussions · security advisory (not public issues)

---

Star history

---

Credits

• LLM layer: @earendil-works/pi-ai · Agent runtime: @earendil-works/pi-agent-core
• Inspired by openclaw/openclaw and NousResearch/hermes-agent

---

_{Made with care by xopcai · xopc.ai}