tingly-box

Tingly Box

Quick Start • Features • Integration • Documentation • Issues

Tingly Box connects any agent to any model — for you and your whole team, with built-in power-ups.

Key Features

• Any Agent ⇄ Any Model
• Unified endpoint for AI — bridge any providers, with protocols translated both ways
• One-click config for Agents — Claude Code, OpenCode, Codex, Xcode, and more
• Profiles for Claude Code — switch models for different scenarios
• Both API keys and OAuth — use your existing quotas anywhere
• Smart Routing — route across models and tokens by cost, speed, or custom policies
• Team AI Management
• Shared team endpoint with centrally managed model rules
• Dedicated keys per member, with data isolated per user
• Per-member usage tracking
• Power-ups
• Guardrails, MCP Gateway, and Usage Analytics
• Image API — image generation and editing through the same gateway, with a built-in playground
• Remote Control — drive agents via Telegram, Weixin, WeCom, Feishu, Lark, and DingTalk
• Production-Ready
• VModel (Virtual Model) — for testing, validation, and benchmarking
• Harness-driven for robustness across protocols, routing, and clients
• UX-first visual management of providers, models, team, and remote bots
• Blazing fast — typically adds < 1ms of overhead

Preview

Quick Start

English | 中文 | Fault Record

Install

Install globally with npm (recommended)

npm install -g tingly-box@latest   # --registry=<mirror> works here too

tb start   # tb = tingly-box; runs in the background (--no-daemon for foreground)
tb open    # open the web UI

# update: reinstall, then restart to apply
npm install -g tingly-box@latest
tb restart

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

Run with npx

# One command: fetch, restart the server in the background, migrate and open the web UI
# (a golang binary release; npx wraps the cli for convenience)
npx tingly-box@latest

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

# the binary for your platform comes from npm too (no GitHub download),
# so an npm mirror is all you need for CN (one of below)
npx --registry=https://registry.npmmirror.com -y tingly-box@latest
npx --registry=https://mirrors.huaweicloud.com/repository/npm/ -y tingly-box@latest
npx --registry=http://mirrors.tencent.com/npm/ -y tingly-box@latest

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

For Docker Compose (recommended for isolated env), building your own image, or troubleshooting — see the Docker Guide.

Integration Guide

Agent Integration - Claude Code / Claude Desktop / OpenCode / Codex / Xcode / VSCode / OpenClaw

• Claude Code (support 1-click config)
• OpenCode (support 1-click config)
• Xcode (require manual config)
• ……

Any application is ready to use.

We've provided detailed config guide in application

Team - Shared Model Deployment

Give your whole team one endpoint backed by centrally managed model rules. Each member gets a dedicated Team Key, and usage is tracked per user.

1. Open Web UI like http://localhost:12580
2. Navigate to Team, configure the model rules, then hand out keys via Team Keys
3. Track per-user consumption under Dashboard → Team usage

Image API

Route image generation and editing through the same gateway. Point any OpenAI-compatible image client at http://localhost:12580/tingly/imagegen and pick the upstream image models with rules, like any other scenario. Try prompts right away in Image → Playground.

DeepSeek Best Compatibility

DeepSeek is optimized for mainstream agent workflows, offering broad compatibility across protocol adapters, agent clients, extended context, vision, web search, and cache optimization.

Module · Status · What It Solves Model List · ✅ Supported · Keeps the official model list up to date in real time Protocol Adaptation · ✅ Supported · Supports official Anthropic/OpenAI APIs with bidirectional conversion Reasoning Capability · ✅ Supported · Provides compatibility with Thinking workflows Cache Hit Optimization · ✅ Supported · Improves cache hit rates for DeepSeek requests Vision Proxy · ✅ Supported · Enables DeepSeek to understand and process images Web Search · ✅ Supported · Calls official Web tools through the Anthropic endpoint 1M Context Window · ✅ Supported · Enables one-click setup for 1M context Codex Adaptation · ✅ Supported · Ensures compatibility with mainstream agent workflows Claude Code / Desktop Adaptation · ✅ Supported · Ensures compatibility with mainstream agent workflows

Supports one-click configuration where available. For applications that require manual setup, detailed in-app configuration guides are provided.

Any compatible application is ready to use.

Detailed configuration guides are available inside each application.

Remote Control Agent via IM Bots - TG / DingTalk / Feishu / Lark / Weixin / WeCom

Tingly Box now supports remote control through popular IM platforms. Interact with your AI agents remotely without direct server access.

Supported Platforms

• ✅ Telegram
• ✅ DingTalk
• ✅ Feishu
• ✅ Lark
• ✅ Weixin
• ✅ WeCom

Quick Setup

1. Open Web UI like http://localhost:12580
2. Turn on Projects under Power-ups in the gear menu at the bottom of the left rail, then open IM in the rail
3. Configure your preferred IM platform bot
4. Start interacting with your agents remotely

Use Cases

• Execute tasks and queries from your phone or any device
• Team collaboration with shared agent access
• Monitor and control agents while away from your workstation

OpenAI SDK

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)

Anthropic SDK

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)

Tingly Box proxies requests transparently for SDKs and CLI tools.

Using OAuth Providers

You can also add OAuth providers (like Claude Code) and use your existing quota in any OpenAI-compatible tool:

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

Requests route through your OAuth-authorized provider, using your existing Claude Code quota instead of requiring a separate API key.

This works with any tool that supports OpenAI-compatible endpoints: Cherry Studio, VS Code extensions, or custom AI agents.

Self-Hosted Model Servers - vLLM / SGLang / Ollama / LM Studio / LocalAI / Jan

Already running your own inference server? Tingly Box connects to it like any other provider and exposes it through the same unified gateway.

Supported out of the box

• vLLM
• SGLang
• Ollama
• LM Studio
• LocalAI
• Jan

Anything else that speaks an OpenAI/Anthropic-compatible API still works via Custom endpoint.

Quick Setup

1. Open Web UI like http://localhost:12580
2. Click Connect AI → pick your engine from the Self-hosted section (default URL and key are pre-filled)
3. Test Connection, then save — it's now usable like any other provider

Web Management UI

Launch the web management interface:

npx tingly-box@latest

Then open http://localhost:12580 in your browser.

Documentation

User Manual – Installation, configuration, and operational guide

Docker Guide – Building, running, and troubleshooting the Docker images

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.

Contributing Guide — Build &amp; Dev

Prerequisites

Tool · Version · Install Go · 1.26+ · https://go.dev/doc/install Node.js · 20+ · https://nodejs.org/ pnpm · latest · npm install -g pnpm task · latest · go install github.com/go-task/task/v3/cmd/task@latest or https://taskfile.dev/installation/

Tip: you can also copy individual shell commands out of Taskfile.yml and run them directly if you prefer not to install task.

1. Clone and init submodules

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