Gemini 4 Carbon is now available.
It’s our strongest model, built to dig deeper, handle long-horizon tasks, and multi-step reasoning.
If Argon is great for complex tasks, Carbon is the model you bring in for your hardest problems.
저희는 Traycer를 사용해 훨씬 사양이 낮은 컴퓨터에서도 수백 개의 에이전트를 동시에 실행하고 있습니다.
현재 사용 중이신 환경에서 어떤 문제가 발생하고 있는지 정확히 파악할 필요가 있습니다. 문제의 원인을 분석할 수 있도록 Help → Report Issue를 클릭해 진단 정보를 보내주시겠어요?
또한, 저희 Discord 서버에 참여하시면 팀으로부터 실시간 지원을 받으실 수 있습니다: https://t.co/ioAm7JsNLq
Your agent can test your mobile app now.
Boot an iOS simulator or Android emulator in Traycer, next to the chat. Tap, swipe and type yourself, or watch the agent drive its device live.
Screenshots from the toolbar; appearance and deep links in Simulator settings.
@Eloitay@Google Need to understand what happened here. Can you please share more details at [email protected]
Or, join our discord, we’ll be able to support you there: https://t.co/2KVN23H3cT
Gemini 4 Carbon is now available.
It’s our strongest model, built to dig deeper, handle long-horizon tasks, and multi-step reasoning.
If Argon is great for complex tasks, Carbon is the model you bring in for your hardest problems.
Dev server on your Linux box. localhost:5173 on your Mac.
Ask a Chat agent to forward the port. It keeps the same port when it can, so OAuth redirects and CORS keep working, and nothing opens to your network.
Works between your own Traycer hosts. No tunnel to set up.
Your laptop doesn't have to run every agent.
Add another supported Mac, Windows or Linux machine as a Traycer host and it shows up next to your laptop. Your Chat agents on different hosts can message each other to split the work.
Today we're introducing Muse Ember, our smallest and most efficient model, built for complex reasoning execution and everyday agent work.
Muse Ember can carry workflows across apps, call tools in sequence, run tests and make targeted code fixes. With a 1M-token context window and native understanding of text, images, audio and video, it can also work across large document sets and varied inputs.
Claude Fable 5.2 just landed in Traycer.
The Claude plan you already have.
That's it.
Stronger coding, reasoning, and vision.
Up to 30% faster than Fable 5.1.
Open Claude Code. Pick Fable 5.2. Go.
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
Your agent built the page. Now you review it without taking screenshots yourself.
Click through the live preview, comment on the exact button, then ask the agent to build a Canvas from it: play the whole flow, sketch on the boards, and send any element back to an agent chat.
Answer a Traycer agent question from your phone lock screen.
Tap the notification, reply on your phone, and the laptop agent keeps going. You can also start a new task from the phone and pick a remote Linux VM as the host.
@woleswoosh@pranshgupta54 We just opened more spots for Gemini Weekend. Claim your $100 of Gemini credits here:
https://t.co/TU3lzfhbm1
Spots are first come, first served, so grab it soon!
@nayeemrahman_ yes you have to select gemini models from Traycer Inference, but first you have to claim the $100 from:
https://t.co/TU3lzfhbm1
(p.s-we just opened more spots, claim fast to use!)