Devin Desktop (@devindesktop) / X

Devin Desktop

957 posts

Devin Desktop

@devindesktop

The app to manage fleets of local and cloud agents from one surface. Plan, delegate, review, and ship without leaving your editor. Built by @cognition

Silicon Valley

Joined October 2024

Affiliates Replies Media

Pinned
Devin Desktop
@devindesktop
Jul 27
Try Kimi K3 in Devin Desktop and the Devin CLI.
Cognition
@cognition
Jul 27
Kimi K3 is now available in Devin Desktop and CLI. On FrontierCode 1.1, Kimi K3 is the first open source model we tested that approaches frontier-level performance.
Devin Desktop
@devindesktop
Jul 21
Devin has always had its own machine. Now, it can run on yours.
Cognition
@cognition
Jul 21
Introducing Devin Outposts: run Devin on any machine. Your Mac mini, a GPU box in your lab, a VM inside your private network, or a Kubernetes cluster next to your internal services.
GIF
Devin Desktop
@devindesktop
Jul 17
Inkling and Grok 4.5 are also available in Devin Desktop and CLI
Cognition
@cognition
Jul 17
The FrontierCode leaderboard is now live: a dedicated page that tracks which models are writing code you’d actually merge. All scores — including Grok 4.5 and Inkling — are available, along with full methodology and sample tasks.
Devin Desktop
@devindesktop
Jul 9
GPT 5.6 is now available in Devin Desktop!
Cognition
@cognition
Jul 9
GPT-5.6 is now available in Devin! On FontierCode 1.1 Extended, the GPT-5.6 family stands out for pairing strong scores with excellent cost efficiency. GPT 5.6 Sol reaches top performance at nearly half of the cost of the next best model.
Devin Desktop
@devindesktop
Jul 8
SWE-1.7 is now available in Devin Desktop and Devin CLI. It achieves near-frontier performance at a fraction of the cost. And you can use lightning mode at 1000 tok/s!
Cognition
@cognition
Jul 8
Introducing SWE-1.7, the most capable model we’ve trained yet. It scores within a few points of the strongest frontier models at a fraction of the cost, and is now available at 1000 tok/s. RL is not hitting its limit: after refining our recipe, we keep seeing gains as we scale
See @devindesktop's full profile
Sign up
Log in

See @devindesktop's full profile

See @devindesktop's full profile