Skip to main content
xbot
Self-hosted · One agent, every channel

Put your AI agent
on your own server

Configure it once and the whole team talks to the same agent through Feishu / QQ / browser / terminal. It calls tools, reads and edits files, runs commands and delegates sub-agents — your data never leaves your host.

Paste this prompt into your agent Claude Code · Codex · Cursor …
Install and start xbot on this machine:
curl -fsSL https://raw.githubusercontent.com/ai-pivot/xbot/master/scripts/install.sh | bash
One command: Web UI + every built-in plugin · Other ways to install
xbot web UI: multi-session sidebar with tool calls and iteration progress

A real session: multi-turn chat · tool calls (Grep / FileReplace / Shell) · per-iteration reasoning · parallel sessions

Why xbot?

Most AI coding agents live in a terminal. xbot doesn't — one agent, every channel.

xbotCodex / Claude Code / OpenCode
Multi-channelFeishu · QQ · Web · CLITerminal only
Shared team LLMAdmin configures once, everyone uses itEveryone brings their own API key
Self-hosted Data never leaves your server
Feishu integrationDocs, Base, Drive, interactive cards
Sub-agents + group chatDelegate, parallelize, debateSub-agents only
Plugin systemTools, hooks, widgets, channel pluginsLimited
Important
The most common setup: run in server mode → connect a Feishu app → the whole team chats with the bot in a group, no individual API keys required.

Core features

Agent capabilities that work out of the box, plus the engineering details production deployments need.

Multi-turn chat + tool calling

Shell, file I/O, web search, cron jobs and sub-agent delegation — with per-iteration reasoning and tool results.

Every channel

The same agent over Feishu / QQ / terminal / browser, with per-session isolation.

Shared LLM subscriptions

Configured once by an admin, used by the whole team — multiple subscriptions, per-model switching and context quotas.

Full-featured TUI

Mouse support, command palette (Ctrl+K), multi-session sidebar and a theming system.

Truly self-hosted

One command to install. SQLite single-file storage — a backup is a file copy.

Extensible

Skills, sub-agents, the MCP protocol and a plugin system (tools / hooks / widgets / channels).

AI-native configuration

The agent can reconfigure itself and its UI through the config and tui_control tools.

Shareable plugin panels

Plugins can produce shareable panels and mint public links — only explicitly shared content gets a token.

Which channel should I use?

One agent core, four ways in — pick whatever fits your workflow.

CLI

For developers: full TUI, streaming output, tool calls.

Feishu

For teams: chat in a group, interactive cards and doc integration.

Web

For anyone with a browser: sign-up / login, invite-only, mobile-friendly.

QQ

For individuals and small groups, via NapCat.

Other ways to install

Windows: irm https://raw.githubusercontent.com/ai-pivot/xbot/master/scripts/install.ps1 | iex  ·  Behind the GFW: curl -fsSL https://ghfast.top/https://raw.githubusercontent.com/ai-pivot/xbot/master/scripts/install-cn.sh | bash

Then open http://localhost:8082 → create an account → gear icon → LLM → base URL / API key / pick a model → chat. Optional flags (the defaults are usually what you want) and every config key → Install & configure.

Executable install guide for AI agents (assertable steps, headless LLM setup, troubleshooting) → Agent install guide. The installer prints that URL as its final output, so an agent given the prompt above knows what to read next.

Architecture

The backend is a pure RPC client interface (zero business logic); the transport layer does the real work.

Feishu · QQ · Web · CLI channels
Dispatcher channel/
Agent Loop agent/ · Transport
LLM llm/
Agent Loop calls → tools/ memory/ skills/ plugins/

Read the full architecture overview.

Community

Questions, feature requests, or just want to chat.