返回目錄

tingly-box

維護狀態: 活躍

tingly-dev/tingly-box

智慧體編排閘道器,連線智慧體與 LLM,支援遠端控制。

前往 GitHub
$ npx tingly-box@latest

347

星數

40

Fork

Go

語言

MPL-2.0

授權條款

2025-11-21

建立於

2026-09-08

最近推送

MPL-2.0 的 Go 語言 LLM 閘道,對 DeepSeek 提供深度相容:npx/Docker 一鍵安裝,程式碼代理接入其 OpenAI/Anthropic 相容端點,本機 Web UI 管理路由。

DSH 整合

相容

作者聲明

安全稽核

未稽核

最後核實

2026-08-21

授權條款

MPL-2.0

01它能幫你完成什麼?

  • Give coding agents a unified model endpoint with DeepSeek best compatibility

    OpenAI- and Anthropic-compatible endpoints (http://localhost:12580/tingly/openai/v1 and /tingly/anthropic) with protocol translation, Thinking-workflow reasoning support, cache-hit optimization, vision proxy and web search for DeepSeek

    Developers running DeepSeek models in coding agents who want one local endpoint with broad protocol compatibility

  • Wire coding agents to the gateway with one click

    One-click configuration for Claude Code and OpenCode (manual guides in-app for Xcode and others), with transparent proxying for SDKs and CLI tools

    Teams using coding agents or custom AI tools that need a quick, low-friction model endpoint setup

  • Control AI agents remotely from IM apps

    Remote task execution and monitoring through Telegram, DingTalk, Feishu, Lark, Weixin, WeCom, Slack and Discord bots configured in the web UI's Remote section

    Builders who want to run and check on agents from a phone or share agent access across a team

02如何將外掛接入 DeepSeek Harness?

先決條件

  • Node.js LTS with npx for the recommended install path (the README provides install steps via nvm for macOS/Linux and winget or nodejs.org for Windows); or Docker for the container paths
  • Go 1.26+ only applies to building from source (source build is documented under the Contributing Guide)

安裝步驟

  1. 01

    Run `npx tingly-box@latest` (or `npx -y tingly-box@latest`) — installs and runs the binary, auto-restarts, migrates and opens the Web UI when run without args

    $ npx tingly-box@latest

  2. 02

    If you hit network issues, use the bundled binary: `npx -y tingly-box-bundle@latest` (CN npm mirrors are supported, e.g. `npx --registry=https://registry.npmmirror.com -y tingly-box-bundle@latest`)

    $ npx -y tingly-box-bundle@latest

  3. 03

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

  4. 04

    Or use Docker Compose for an isolated environment: `docker-compose up -d` (Web UI at http://localhost:12581; `docker-compose down` to stop)

  5. 05

    Open the Web UI at http://localhost:12580 and configure providers, routes and agent integrations there

驗證整合成功

作者未說明

03DSH 整合程度與能力邊界

DSH 整合相容

Runs as a standalone local LLM gateway beside DSH (not installed inside the harness): agents connect to its OpenAI/Anthropic-compatible endpoints, while the repo is tagged as a dsh plugin and the README documents DeepSeek best compatibility

  • Agent-first model gateway

    model providers (API keys and OAuth providers like Claude.ai / Codex)unified OpenAI/Anthropic-compatible endpoint for agents with automatic protocol translation; adds typically < 1ms of overhead

    proxies requests to remote model providers (network egress); stores per-user configuration and usage data locally
  • Smart routing engine

    models, tokens and custom policiesrequests routed across models and tokens based on cost, speed, or custom policies — beyond simple load balancing

  • Visual control plane (Web UI)

    browser on http://localhost:12580manage providers, routes, aliases, models and remote bots at a glance — no config files needed; includes client-side usage analytics (token consumption, latency, cost estimates)

    writes configuration locally instead of config files
  • Local stdio MCP web tools

    an MCP clientlocal stdio MCP server exposing `web_search` / `web_fetch` tools

    fetches web content over the network when called

04適合誰?何時不該用?

適合

  • Developers running DeepSeek models in coding agents who want one local endpoint with broad protocol compatibility
  • Teams using coding agents or custom AI tools that need a quick, low-friction model endpoint setup
  • Builders who want to run and check on agents from a phone or share agent access across a team

不適合

  • Known issues have been recorded in a public fault record; the maintainers ask users to update to the latest version to resolve them, so staying on the latest release is effectively required.

05相容性、維護與安全提醒

  • Known issues have been recorded in a public fault record; the maintainers ask users to update to the latest version to resolve them, so staying on the latest release is effectively required.
  • The gateway serves local agents but forwards requests to remote model providers, so it needs network access and valid API keys or OAuth authorizations for the providers you route to.
  • The recommended install path requires Node.js LTS with npx; container paths require Docker, and Docker Compose uses port 12581 to avoid conflicting with a host install on 12580.
2025-11-212026-08-19v0.260819.0

MPL-2.0 · actively maintained (latest release v0.260819.0, 2026-08-19)

06常見問題

Tingly Box 如何與 DeepSeek Harness 搭配?

Tingly Box 作為獨立本機閘道執行在 harness 旁邊,而不是安裝到 harness 內部:代理程式連接它的 OpenAI/Anthropic 相容端點(http://localhost:12580/tingly/openai/v1 或 /tingly/anthropic)。儲存庫標記為 dsh plugin,README 也說明了 DeepSeek 最佳相容性——協定轉接、推理思考鏈、快取最佳化、視覺代理、網頁搜尋和 1M 上下文。

安裝前需要準備什麼?

推薦的 `npx tingly-box@latest` 安裝方式需要 Node.js LTS 與 npx;容器方式需要 Docker / Docker Compose。只有從原始碼建置時才需要 Go 1.26+。

請求和資料會流向哪裡?

閘道在本機 12580 連接埠執行,把請求透明代理到你透過 API Key 或 OAuth(Claude.ai、Codex 等)設定的模型供應商;設定與每位使用者的用量資料儲存在本機。Guardrails 文件介紹了基於策略的安全檢查與敏感憑證遮罩。

支援 MCP 嗎?

支援——Tingly Box 附帶一個本機 stdio MCP 伺服器,提供 `web_search` / `web_fetch` 工具,詳見 docs/mcp-web-tools.md。

有哪些限制?

已知問題記錄在公開的 fault record 中,維護者要求更新到最新版本來解決。此外閘道需要連網,並且你路由到的模型供應商要有有效的 API Key 或 OAuth 授權。

08資料與來源

  • 作者聲明github.combfdaacf68890…

    DeepSeek is optimized for mainstream agent workflows, offering broad compatibility across protocol adapters, agent clien…

  • 作者聲明github.combfdaacf68890…

    Tingly Box **serves agents, coordinates AI models, optimizes context, and routes requests** for maximum efficiency — wit…

此頁面根據專案公開文件、儲存庫中繼資料與 DSH Plugins 的結構化解析所產生;最後核實於 2026-08-21。發現錯誤?提交更正。

🏆

最佳 DeepSeek Harness 外掛

從全目錄挑出的 12 個值得優先安裝的外掛,涵蓋各個分類。

DSH Plugins 是獨立的 DeepSeek Harness 外掛市集,與 DeepSeek 官方無關,也不代表官方背書。第三方外掛未經安全稽核,安裝前請審查原始碼。

每週取得最新的 DeepSeek Harness 外掛,絕不濫發。