TrendWhat rose on GitHub, every day at 07:30 KST · 한국어

GitHub · as of November 8, 2026 · View on GitHub →

pingdotgg/t3code

AI coding agent control surface

#7 on GitHub's weekly trending, November 8, 2026 · +14,955 stars in 7 days · trending 22 of the last 30 days

Stop and direct AI coding agents on your home computer from a subway

You can stop an AI coding task running on your home computer or issue new instructions while riding the subway to work. T3 Code is a tool that bundles multiple AI coding tools installed on your computer into a single app for remote management. It serves as an interface to control the environment where agents run, handling various tools without being tied to a specific AI model.

Multiple AI coding tools in one view

T3 Code supports several AI coding tools, including Claude Code, Codex, Cursor, Grok Build, OpenCode, Google Antigravity, and fx. If each tool is installed on your computer and authentication is complete, T3 Code controls them from a single screen. Users can manage their workflow from an integrated interface without switching between individual tool terminals to enter commands. This is particularly useful for developers who use multiple AI tools concurrently.

Installation and execution

Installation is performed via command line or package manager depending on the operating system. On macOS and Linux, you can run the installation script with the curl command or enter brew install --cask t3-code using Homebrew. On Windows, you can use the irm command in PowerShell or install via winget and scoop. After installation, running the t3 command starts the server and opens the local web app. To run it as a background service, use t3 service install.

Characteristics of an early-stage project

This project is still in a very early stage, so bugs may occur. The development team is currently accepting contributions only for small fixes rather than major feature additions. There is no documentation site yet, and detailed usage instructions must be referenced in the docs/ folder within the repository. Specific settings such as remote access, permission modes, and keyboard shortcuts can be found in that documentation. To build from source, you must install the Vite+ based vp tool.

Pre-usage checks

Before using T3 Code, you must ensure that at least one AI coding tool is installed and authenticated. You should pre-run each tool's login command (such as codex login or claude auth login) so that T3 Code can recognize them. Additionally, since the project is in an early stage, it is advisable to establish a backup strategy to prevent data loss or errors in critical tasks. The README does not contain explicit information regarding the license or long-term support scope.

Written by AI from this repository's README on November 1, 2026. For the facts, the original on GitHub is the reference.

By the numbers

GitHub trending history
64 days between Jun 19, when Trend began recording, and Nov 8, 2026 · 22 of the last 30 days · first on Jul 12 · best daily rank #4 (Oct 31)

Read from GitHub, as of November 8, 2026.

Language
TypeScript
Stars
52,207
Stars gained in 7 days
+14,955
Contributors
925
Forks
9,981
Latest release
v0.1.7 · November 4, 2026
Commits
9,730
Last commit
November 8, 2026
Open issues
1,982
Open pull requests
3,947

View on GitHub → · Homepage

README badge

trend.ondo.sh · GitHub daily trending #4 · October 31, 2026

The badge above shows the highest this repository has ranked on GitHub's daily trending since June 19, 2026, and the day it did. Paste the Markdown below into your README. The badge opens this page, and it updates by itself when the repository climbs higher.

[![trend.ondo.sh](https://trend.ondo.sh/github/r/pingdotgg--t3code/badge.en.svg)](https://trend.ondo.sh/github/r/pingdotgg--t3code/en.html)