Announcement: Here is fault record. Please update to the latest version to resolve known issues. Thank you for your continued support.

Tingly Box

Quick Start • Features • Integration • Documentation • Issues

Tingly Box serves agents, coordinates AI models, optimizes context, and routes requests for maximum efficiency — with built-in remote control and secure, customizable integrations.

Key Features

• Agent-First Model Gateway – Unified endpoint for agents — seamlessly bridge OpenAI, Anthropic, Google Gemini, and more with automatic protocol translation and native agent compatibility
• Agent Integration – One-click config for Claude Code, OpenCode, Codex, Xcode, and more — transparent proxying for SDKs and CLI tools
• Agent Profiles - Run agent like Claude Code with individual profiles, each profile can work with different model and agent config
• Remote Control via IM Bots – Control AI agents remotely through Telegram, DingTalk, Feishu, Lark, Weixin, WeCom, Slack, and Discord
• Multi-Tenant API Tokens – Isolate data per user with dedicated API tokens — each user gets their own usage tracking, provider access, and configuration
• Smart Routing Engine – Intelligently route requests across models and tokens based on cost, speed, or custom policies — far beyond simple load balancing
• Flexible Authentication – Support for both API keys and OAuth providers (Claude.ai, Codex, etc.) — use your existing quotas anywhere
• Visual Control Plane – Intuitive web UI to manage providers, routes, aliases, models, and remote bots at a glance — no config files needed
• Client-Side Usage Analytics – Track token consumption, latency, cost estimates, and model selection per request — directly from your client
• Blazing Fast Performance – Adds typically < 1ms of overhead — get flexibility without latency tax

Quick Start

English | 中文

Install

From npm / npx (recommended)

# Install and run (auto restart, migrate and open webui while run without any args)
# A golang binary release but npx to wrap cli for convenience
npx tingly-box@latest

# or -y for convenience
npx -y tingly-box@latest

# if any network trouble, try bundle with binary built-in
npx -y tingly-box-bundle@latest

# npm mirror is supported for CN (one of below)
npx --registry=https://registry.npmmirror.com -y tingly-box-bundle@latest
npx --registry=https://mirrors.huaweicloud.com/repository/npm/ -y tingly-box-bundle@latest
npx --registry=http://mirrors.tencent.com/npm/ -y tingly-box-bundle@latest

if any trouble, please check tingly-box output, or call for an issue to help.

Install Node & NPX

# MacOS & Linux
## Install Node.js LTS via nvm
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/master/install.sh | bash

## Restart terminal or load nvm
source ~/.nvm/nvm.sh

## Install Node.js LTS
nvm install --lts

## Verify installation
node -v
npx -v

# Windows
## Powershell with Winget
winget install OpenJS.NodeJS.LTS

## Restart terminal, then verify installation
node -v
npx -v

## Or download and install Node.js LTS manually:
https://nodejs.org/en/download

From Docker (GitHub Host)

mkdir tingly-data
docker run -d \
  --name tingly-box \
  -p 12580:12580 \
  -v `pwd`/tingly-data:/home/tingly/.tingly-box \
  ghcr.io/tingly-dev/tingly-box

From Docker Compose (Recommend for isolated env)

# Build and start in detached mode
docker-compose up -d

# View logs
docker-compose logs -f tingly-box

# Stop services
docker-compose down

# Access Web UI at http://localhost:12581
# (Note: Port 12581 is used to avoid conflict with host tingly on 12580)

Integration Guide

from openai import OpenAI

client = OpenAI(
    api_key="your-tingly-model-token",
    base_url="http://localhost:12580/tingly/openai/v1"
)

response = client.chat.completions.create(
    model="tingly-gpt",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response)

from anthropic import Anthropic

client = Anthropic(
    api_key="your-tingly-model-token",
    base_url="http://localhost:12580/tingly/anthropic"
)

response = client.messages.create(
    model="tingly",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response)

# 1. Add Claude Code via OAuth in Web UI (http://localhost:12580)
# 2. Configure your tool with Tingly Box endpoint

npx tingly-box@latest

Documentation

User Manual – Installation, configuration, and operational guide

Guardrails – Policy-based safety checks, built-in protections, and protected credential masking

MCP Web Tools – Local stdio MCP server for web_search / web_fetch

Contributing

By contributing to this repository, you agree that your contributions may be included in this project under the MPL-2.0 and may also be used by Tingly Inc. under separate commercial licensing terms.

See CONTRIBUTING.md and NOTICE for details.

We welcome contributions! Check the steps below to build from source code.

git clone https://github.com/tingly-dev/tingly-box.git
cd tingly-box
git submodule update --init --recursive

task web:mock
# or directly:
cd frontend && pnpm install && pnpm dev:mock

task web
# or directly:
cd frontend && pnpm install && pnpm dev

task start
# or directly:
go run ./cli/tingly-box --verbose start --debug --port 12580 --browser=false

task build

task wails:build

task swagger        # Regenerate openapi.json from Go source
task codegen        # Regenerate frontend API client from openapi.json
task go:test        # Run Go unit tests

Support

Telegram	Wechat
https://t.me/+V1sqeajw1pYwMzU1	tingly-box

Early Contributors

Special badges are minted to recognize the contributions from following contributors:

Contributors

License

This project is available under:

• MPL-2.0 · © Tingly Dev – See LICENSE.txt
• Commercial License · © Tingly Dev – See LICENSE-COMMERCIAL.txt

For commercial licensing inquiries, contact biz@tingly.dev.

❤️ Support Tingly Box

If Tingly Box has been useful to you, consider supporting its development.

Donations are optional. A ⭐ on GitHub or a contribution is just as appreciated.

WeChat Pay	Alipay