thatsimpletech/tst-desk

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

0 stars Качество 66 Тренд 20Apache-2.0

Обзор

TST Desk is a desktop application that gives you an AI coworker in a window: you point it at a folder, type what you want, and watch it work — reading files, running commands, and asking before it does anything consequential. It looks and feels like Claude Desktop with a Cowork-style workspace, but it runs on models you choose through any OpenAI-compatible endpoint, billed to your API key, with a live cost meter in the title bar. There is no server, no hosted backend, no account, and no subscription — and pointed at a local model server it needs no API key and no network at all. v0.1.0 is on the releases page. Each platform gets these artifacts, built by .github/workflows/package.yml: GitHub Releases rewrites spaces in Tauri's TST Desk_… names to dots; SHA256SUMS.txt uses the download names. 1. Download the artifact for your platform from the releases page. 2. Verify it against the published SHA256SUMS.txt. 3. Install it: - — open the .dmg, drag to Applications.

README

Показан фрагмент оригинального README. Открыть оригинал.

TST Desk

An open-source, bring-your-own-model desktop agent workspace.

Point it at a folder, say what you want, and watch it work. It reads files, runs commands, and asks before it does anything consequential. It looks and feels like Claude Desktop, but it runs on the models you choose, billed to your own key.

Open source, no account. Apache-2.0. Nothing to sign up for, no hosted backend, no subscription. You pay your model provider per token, and nobody else.
Any OpenAI-compatible model. Paste a server URL, pick a model, start working. A live meter in the title bar shows what each turn and session costs, and a spend cap pauses the session when it is reached.
Works offline with a local model. Pointed at a model server on your own computer, it needs no API key and no network.
Asks before it acts. Every tool call goes through a classifier. Reads and edits inside your folder run on their own. Other shell commands, anything outside the folder, and anything it cannot classify wait for your approval.
Keys stay in your OS keychain. Keychain on macOS, Secret Service on Linux, Credential Manager on Windows. Never in a config file or a log.
A native app for macOS, Linux and Windows. Built on Tauri: a Rust shell on the system webview, with the agent daemon bundled in. No Electron. An Android app pairs with a QR code and follows your sessions from your phone.

Download the latest release · Install steps · Quickstart · How models work

Works with

TST Desk talks to any server that speaks the OpenAI chat API. No model ships with it; the first run walks you through adding one.

What	Examples	Key
A model server on your computer	Ollama, vLLM, LM Studio, llama.cpp’s server	None. No key is asked for, and none is sent to `127.0.0.1` or `localhost`.
A hosted model API	A provider’s OpenAI-compatible `/v1` endpoint	Your key, stored in the OS keychain and sent only to that URL
A gateway in front of many models	A router or proxy that speaks the OpenAI chat API	Your key for the gateway
A server you run on another machine	Your own vLLM or llama.cpp behind a key	A named key for that server
Anything else	Any endpoint that speaks the OpenAI chat API	Whatever that endpoint needs

You can also mix them: a team gives planning, doing and checking their own models, for example a hosted model that plans and a local one that does the work. See docs/models.md.

Install

Get the newest build from the latest release. Every release has these files:

Platform	File
macOS, Apple silicon	`.dmg` (`aarch64`)
macOS, Intel	`.dmg` (`x64`)

Открыть полный README на GitHub

Установка

npx skillfish add thatsimpletech/tst-desk

Новичок в MCP? Начните с руководства на mcpskill.org →