agent-browser
A fast browser-automation CLI built for AI agents.
T3 Code — проект с открытым исходным кодом из категории «ИИ-агенты» от pingdotgg (pingdotgg/t3code на GitHub). У него 61 138 звёзд на GitHub и 10 980 форков, он распространяется по лицензии MIT и последний раз обновлялся на GitHub 15 ноября 2026.
One fast interface for every coding agent on your machine — desktop, web and phone, MIT
Run it once with npx and see your agents in one place.
macOS, Windows and Linux builds, or a package manager per platform.
Any agent already installed and signed in on your machine shows up automatically.
The same threads, on iOS and Android, with approvals from anywhere.
Claude Code, Codex, Cursor, OpenCode, Grok Build, Antigravity, Pi, Muse Code and any ACP agent, in one interface.
T3 Code drives the agents you already pay for — it resells no tokens and ships no model of its own.
One server, and every client shows the same threads — start at your desk, approve from your phone.
Each thread can work in its own worktree; review the diff, then commit, push and open a pull request with one button.
Run agents on any machine and connect over your local network, Tailscale or T3 Connect.
Performance is treated as a feature — a dropped frame counts as a bug, not a quirk.
Run it without installing anything.
npx t3@latestInstall the desktop app with Homebrew.
brew install --cask t3-codeOr install with winget on Windows.
winget install T3Tools.T3CodeTwo more from the same shelf: agent-browser — A fast browser-automation CLI built for AI agents, and claude-mem — Give your coding agents a persistent memory that. Browse every AI Agents tool in the catalogue to compare the category. Before running a model locally, check how much VRAM you need for local LLMs — model size has to match your hardware.
An open-source control surface for coding agents: it drives the agent CLIs already installed on your machine through one desktop, web or phone interface.
No. It ships no model and resells no tokens — it controls Claude Code, Codex, Cursor and other agents you already subscribe to.
Yes, MIT licensed. You still pay the agent providers you use; T3 Code itself costs nothing.
Yes — iOS and Android apps show the same threads as the desktop, so you can approve steps away from your desk.
It is early (0.1.x) and shipping fast, with nightly builds and a large open-issue list — expect bugs and rapid change.
A fast browser-automation CLI built for AI agents.
Give your coding agents a persistent memory that survives every session.
The open source coding agent
ZCode — Z.ai's AI coding workspace: desktop app, browser interface and terminal agent in one open-source harness
Every agent's model, one place — run Claude Code on Kimi, Codex on DeepSeek, with quota failover, MIT
Alibaba's in-page GUI agent: control any web interface with natural language, from one script tag
Другие проекты из категории «ИИ-агенты» с наибольшим числом звёзд в каталоге LibreAI — реалистичный список альтернатив, если T3 Code вам не подходит.
A personal AI that really does things — on any OS, with your data staying yours.
Matt Pocock's engineering skills for coding agents — grill the spec first, then build it right, MIT
An agentic skills framework & software development methodology that works.
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
The agent that grows with you — a Python framework for adaptive AI agents.
Соседние проекты из категории «ИИ-агенты» в каталоге, ближайшие по числу звёзд к T3 Code — продолжайте изучать полку по обе стороны от него.
A programming framework for agentic AI
The best-benchmarked open-source AI memory system. And it's free.
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work…
Drop-in persistent memory infrastructure for AI agents and apps.
Make any software agent-native: generate a CLI so agents can drive the apps you already use
Бесплатно и открыто — забирайте исходный код, ставьте звезду репозиторию и начинайте создавать.