Price terms as published
Each line is the vendor’s own wording, split from the price capture checked on 2026-10-16. Nothing here is rounded, converted or re-worded — the full sentences stay in the review below. Lines that carry only a price continue the plan named on the line above, in the vendor’s own order.
| # | Plan / term | Checked |
|---|---|---|
| 1 | Free (open source) | 2026-10-16 |
| 2 | requires existing agent subscriptions | 2026-10-16 |
One-liner: T3 Code is an open-source mobile and web companion that lets you watch, approve, and steer coding-agent tasks from your phone — while the actual agent runs on your desktop computer.
Verified facts (checked 2026-10-16)
| Attribute | Value | Source |
|---|---|---|
| GitHub stars | 27,809 | pingdotgg/t3code via GitHub API |
| License | MIT | LICENSE file, verified same day |
| Created | 2026-02-08 | GitHub API |
| Last push | 2026-10-16 | GitHub API (daily commits) |
| Supported agents | Claude Code, Codex, Cursor, Grok Build, OpenCode, Google Antigravity | README |
| Platforms | iOS App Store, Android Play Store, web (app.t3.codes), Electron desktop | README + app stores |
| Price | $0 — free and open source | GitHub repo |
The README is explicit: “Works with your subscriptions on Claude Code, Codex, Cursor, Grok Build, OpenCode, and Google Antigravity. If they’re set up on your computer, T3 Code can control them.”
What “free” actually means
T3 Code is a remote control and monitoring layer, not an agent itself. It doesn’t come with any models and doesn’t charge for anything. You install it on your phone, pair it with a desktop daemon, and then you can see what your coding agent is doing and approve steps from anywhere.
The costs are all upstream:
- You need at least one coding agent subscription already active on your machine
- Each additional agent you connect is another monthly bill
- T3 Code adds no markup, no credits, no per-request fees
What the marketing claims don’t say
- Your computer has to stay on. T3 Code is a remote panel, not a cloud runner. If your laptop goes to sleep or loses internet, the agent stops and your phone goes dark.
- It’s a view + approve layer, not a full IDE. You can see diffs, approve/reject changes, and send short messages. You’re not doing full file editing or multi-file refactors from the phone app — that still happens on the desktop.
- Provider terms still apply. Controlling Claude Code or Codex through a third-party mobile app doesn’t change what the provider’s TOS allows. If a provider bans third-party frontends, T3 Code could break for that agent overnight.
Who should use it
Developers who already have a coding agent running on their machine and want to check in on long-running tasks (refactors, migrations, large feature builds) while away from their desk. It’s a quality-of-life upgrade, not a standalone tool.
Repository stats and feature claims verified against primary sources on 2026-10-16. This entry follows our verification policy: every claim was checked against primary sources, not copied from other reviews.