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
- Tweets 987
- Following 23
- Followers 82,290
- Likes 1,175
Fusion in Devin Desktop & CLI
Fusion achieves frontier intelligence while being up to 39% cheaper.
Use your favorite frontier model for planning and a cost-effective model for execution.
Fable/Astra + SWE-2 is very cost-effective during SWE-2’s free promo.
Introducing Fusion in Devin CLI
The most efficient frontier harness for Fable & Astra; 39% cheaper across coding benchmarks.
Pick your favorite model for planning and a cost-effective model for execution.
19
16
257
20,878
The Devin CLI has a brand new model picker! You can now set your model, tune its reasoning effort, and compare costs - all in one view
Try it today with `/model`
24
26
341
28,488
GPT-5.6 Sol is now 70% off in Devin Desktop and Devin CLI, through October 3.
On FrontierCode 1.1, Sol achieves top-tier results. With this promo, it's one of the most cost-effective frontier models you can run in Devin.
52
81
1,091
227,634
We're making SWE-1.7 and GLM-5.2 free for the next month!
All Pro, Max, and Teams users can keep using both models in Devin Desktop and Devin CLI.
96
70
1,104
109,444
Kimi K2.7 Code and GLM 5.2 are available in Devin Desktop and CLI
Both perform strongly on FrontierCode Extended, our benchmark for real-world engineering tasks:
GLM 5.2: 43.0%
Kimi K2.7 Code: 39.5%
Pro/Max/Teams users can try both models for free until July 5
31
46
450
804,430
At @tryramp, engineers use Devin Desktop to bring their favorite agents into one place.
With Devin Desktop they can dispatch, monitor, and jump between agents from a single surface with shared context across every task.
1
5
75
14,412
Claude Agent now runs inside Devin Desktop.
Start Claude Agent sessions in Devin Desktop, coordinate them with your other agents, and keep context shared from a single command center.
Learn more about using your favorite agents in Devin Desktop:
docs.devin.ai/desktop/acp
2
1
34
7,007
Codex CLI now runs inside Devin Desktop.
You can pair your Codex subscription with Devin Desktop to have native multi-agent orchestration.
Learn more about using your favorite agents in Devin Desktop: docs.devin.ai/desktop/acp
5
1
48
8,034
Devin Desktop is built on the Windsurf IDE. Your settings, extensions, keybindings, LSPs, and workflows carry over.
Most agent work should happen in the background. But when you need to review, debug, or make the last-mile edit, the full IDE is exactly where you need it.
2
2
51
7,650
Devin Desktop supports the Agent Client Protocol (ACP), and is now compatible with Codex, Claude Agent, OpenCode, and any other ACP-compatible agent.
This lets users manage multiple agents from one surface and share context between them.
8
5
96
13,557
Introducing Devin Desktop: the next generation of Windsurf
Manage fleets of local and cloud agents from one surface
Support for any ACP-compatible agent
With a full IDE for when you need to jump into the code
105
107
945
507,702
Claude Opus 4.7 (fast mode) is now available in Windsurf!
Full Claude Opus 4.7 intelligence
~2.5x higher output speeds
We can't wait to see what you'll build with it!
22
19
211
20,130
Devin Review runs hundreds of thousands of times per day.
Starting today, run it directly from Windsurf: a smart reviewer in your editor, with bugs and context in one place.
Also launching Quick Review: 10x faster bug detection powered by SWE-check, available only in Windsurf.
27
41
322
118,357
Claude Opus 4.7 is now available in Windsurf 2.0!
Anthropic has clearly optimized Claude Opus 4.7 for sustained reasoning over long runs. Agents stay on track longer without intervention, so engineers can manage multiple agents in parallel instead of working 1:1.
Claude Opus 4.7 model costs will be available at promotional pricing until April 30th across all plans.
Let us know if there's anything else you need from us!
30
34
423
36,369
Devin runs in its own VM in the cloud.
You plan locally, delegate to Devin with one click, and keep coding (or close your laptop). Included with every Windsurf plan.
Access to Devin in Windsurf is rolling out gradually over the next 48 hours.
1
1
66
13,116
Every time you switch tasks, you lose context.
Spaces help you stay in the flow by grouping agent sessions, PRs, files, and context for a project. When you return to a Space, you can pick up where you left off.
2
1
74
14,048
The more agents you run, the harder it gets to track what's running, what's blocked, and what needs review.
The Agent Command Center puts all your agents - local and cloud - in a single Kanban view.
5
9
138
34,973
Introducing Windsurf 2.0.
Manage all your agents from one place and delegate work to the cloud with Devin - so your agents keep shipping even after you close your laptop.
131
182
1,992
21,390,498
When we launched our new quota system, we should have been clearer: your quota and extra usage are billed based on tokens consumed.
To address that, we’re introducing a redesigned model picker that shows exact token pricing upfront, so you can plan your model usage based on the relative costs of each model.
To help you manage token costs better, we also added a prompt cache timer directly in the context window and now show precise token counts on every response card.
2
2
28
5,247
Adaptive is now live - our new intelligent model router.
It automatically picks the best model for every task while avoiding overuse of premium models, so your quota lasts significantly longer.
For the next 2 weeks, we’re offering promotional rates for adaptive to give you a chance to try it out: $0.50 per 1M input, $2 per 1M output, $0.10 per 1M cache read tokens.
We’re rolling out the Adaptive model to all self-serve users today, including Pro, Max, and Teams.
We expect this to be the best default option for most users who want to stay within the quota limits throughout the month, and we’ll continue deploying new updates to improve routing performance.
3
8
63
8,558
GPT-5.4 is live in Windsurf with multiple reasoning efforts!
GPT-5.4 Low is also available in Arena Mode's Frontier and Hybrid Battle Groups.
Let us know what you think!
21
15
354
65,117
Gemini 3.1 Pro is live in Windsurf!
It's also available in Arena Mode's Frontier and Hybrid Battle Groups.
Let us know what you think!
23
20
335
57,564
Claude Sonnet 4.6 is live in Windsurf, with support for 1M token context!
Sonnet 4.6 is also available in Arena Mode’s Frontier and Hybrid Battle Groups.
Let us know what you think!
23
19
365
52,845
GLM-5 and Minimax M2.5 are live in Windsurf!
Limited-time discounts:
- GLM-5: 0.75x credits
- Minimax M2.5: 0.25x credits.
Both models are also available in Arena Mode's Frontier and Hybrid Battle Groups.
18
26
547
65,028
GPT-5.3-Codex-Spark (preview) is now live in Windsurf Arena Mode.
For now, it's exclusively available through the Fast and Hybrid Arena Battle Groups.
25
20
297
41,333
The Arena Mode Public Leaderboard is live!
Top Frontier models:
1. Opus 4.6
2. Opus 4.5
3. Sonnet 4.5
Top Fast models:
1. SWE 1.5
2. Haiku 4.5
3. Gemini 3 Flash Low
Live leaderboard link and analysis below.
25
27
333
77,849
Opus 4.6 (fast mode) is now available in Windsurf in research preview! It's just as smart as regular Opus 4.6 but runs up to 2.5x faster.
Users will have access to promo pricing until Feb 16.
Let us know what you think.
23
21
313
69,695
Opus 4.6 is free in Arena Mode!
And, we've extended the free period for Arena Mode Battle Groups (Frontier, Hybrid, and Fast) through Sunday.
How to get started 👇
18
32
496
46,674
With Arena Mode, you can select specific models to run (up to 5). Credits will be used based on the selected models.
To use Arena Mode for free for the next week, choose a Battle Group. Models like Opus 4.5, GPT-5.2-Codex, and Kimi K2.5 are included in the Frontier group!
Introducing Arena Mode in Windsurf: One prompt. Two models. Your vote.
Benchmarks don't reflect real-world coding quality. The best model for you depends on your codebase and stack. So we made real-world coding the benchmark.
Free for the next week. May the best model win.
17
14
224
43,353
We've also added Plan Mode!
It's fully compatible with Arena Mode so you can find your favorite model for planning.
Pro tip: type "megaplan" in the chatbox for an extra-thorough interactive planning experience.
Introducing Arena Mode in Windsurf: One prompt. Two models. Your vote.
Benchmarks don't reflect real-world coding quality. The best model for you depends on your codebase and stack. So we made real-world coding the benchmark.
Free for the next week. May the best model win.
14
11
266
39,220
Kimi K2.5 is live in Windsurf! And, it's one of the models available in Arena Mode's Frontier Arena.
Let's see if it lives up to the hype!
0x credits for paid users (limited time).
20
16
302
413,569
Arena Mode is part of Wave 14! We've also added Plan Mode to Cascade.
Check out the blog post for more details: windsurf.com/blog/windsurf-w…
3
5
60
12,438
Introducing Arena Mode in Windsurf: One prompt. Two models. Your vote.
Benchmarks don't reflect real-world coding quality. The best model for you depends on your codebase and stack. So we made real-world coding the benchmark.
Free for the next week. May the best model win.
86
102
1,239
1,072,607
GPT-5.2-Codex is now live in Windsurf!
For coding, it's a step up from GPT-5.1-Codex-Max and GPT-5.2.
Available for all users starting at 0.5x credits (limited time discount).
ALT GPT-5.2-Codex is now available in Windsurf, the AI IDE.
32
33
490
74,659
🎁 And last but not least, a Shipmas Gift: SWE-1.5, Available For Free
Our near-frontier model, SWE-1.5, is now available for free to all users. SWE-1.5 Free (codename Penguin Alpha) has the full intelligence of SWE-1.5, with the same coding performance on SWE-Bench-Pro, but delivered at standard throughput speeds. The original variant of SWE-1.5 that his hosted on Cerebras will continue to be available.
For the past few weeks, SWE-1.5 Free has been available to users under the codename Penguin Alpha. The reactions have been encouraging:
3
1
45
5,734
🕯️ Multi-Cascade Panes & Tabs: See All Your Sessions At Once
You can already run multiple Cascade sessions in Windsurf at the same time. Now, you can view and interact with them in separate panes and tabs within the same window. This lets you monitor progress and compare outputs of sessions side-by-side, or even turn Windsurf into one big Cascade session.
1
1
45
12,774
🎄 Git Worktree Support in Cascade
Windsurf now supports Git worktrees, letting you spawn multiple Cascade sessions in the same repository without conflicts. Git worktrees check out different branches into separate directories while sharing the same Git history.
2
2
48
16,243
Introducing Wave 13: Shipmas Edition 🎅
- SWE-1.5 Free: The full intelligence of SWE-1.5 at standard throughput, for free for the next 3 months
- True parallel agents with Git Worktrees + multi-pane and multi-tab Cascade
- Dedicated terminal for more reliable command execution
And many other other new features, bug fixes, and performance improvements.
Happy holidays and merry shipping from the Cognition team!
38
49
489
203,949
GPT-5.2 is now live in Windsurf!
Available for 0x credits for a limited time (paid and trial users).
The version bump undersells the jump in intelligence:
- Biggest leap for GPT models in agentic coding since GPT-5
- SOTA coding model at its price point
- Default in Windsurf
39
37
476
121,152
You can now pair SWE-1.5 with Sonnet 4.5 for planning in Windsurf.
This lets you create hybrid agents that take advantage of SWE-1.5's speed while working together with SOTA models for planning out more complex tasks.
35
33
617
118,411
GPT-5.1 and GPT-5.1-Codex are now live in Windsurf
All paid users get free access for the next 7 days. GPT-5.1 is also set as the default model for new users.
34
41
445
126,370
Codemaps can also be taken literally - visual system diagrams with two way linking strongly grounded in the codebase.
we heard this feedback from Aiden but also our biggest Fortune 500 customers trying to wrangle their codebases
x.lingyaoai.com/aidenybai/status/19850…
see it here: windsurf.com/codemaps/87532a… in the toggle in sidebar
there's significant alpha in better diagraming/exploration tools for understanding codebases. the ones today suck
traditionally done w/ real work or pair programming, but that's slow. practically most engs don't understand the full codebase
3
9
140
94,079
Codemaps is now live!
We have found that by far the largest constraint on your ability code, whether manually or with agents, is your ability to understand the code you are working with.
When you move fast with low understanding, you get slop.
When you move fast and scale understanding with AI, you can truly scale your productive output.
Fight slop with Codemaps.
42
60
754
126,117
Introducing SWE-1.5, our fast agent model.
It achieves near-SOTA coding performance while setting a new standard for speed. Now available in Windsurf.
67
77
730
508,715
You can now try a new stealth model in Windsurf.
Falcon Alpha is a powerful agentic model designed for speed.
We're excited to hear what you think ⚡️
85
49
553
280,056
We trained a first-of-its-kind family of models: SWE-grep and SWE-grep-mini.
Designed for fast agentic search (>2,800 TPS), surface the right files to your coding agent 20x faster.
Now rolling out gradually to Windsurf users via the Fast Context subagent.
61
70
1,135
250,148
Claude Sonnet 4.5 is now available in Windsurf. The model's ability to maximize actions through parallel tool execution makes Cascade Agent runs dramatically faster and more effective.
Now available for 1x credits to individual users for a limited time.
45
83
861
490,238
Today, code-supernova becomes code-supernova-1-million. This new stealth model is a supercharged version of code-supernova that comes with a 1M context window.
Available for a limited time to individual users for free. Excited to hear what you build with it!
34
50
690
73,850
The new @Figma MCP server is now available in the Windsurf MCP Store!
After setting it up (tutorial in video), just paste your Figma links directly into Cascade and it'll turn your designs into code.
13
36
383
547,589
Excited to share that OpenAI’s GPT-5-Codex is now live in Windsurf!
We’re making it free to paid users for a limited time. We can’t wait to hear what you build with it!
62
78
823
670,760
Introducing code-supernova, a versatile agentic coding model that supports image inputs. 200k context window.
Now available for individual users for free for a limited time.
We’re excited to hear what you think!
44
69
721
118,067
Windsurf now has queued messages!
Send follow-up messages for Cascade to pick up when it's done with the current task.
45
27
312
52,996
Grok Code Fast 1 is now available for free in Windsurf for a limited time. Let us know what you think!
74
77
919
178,172
Windsurf now supports dev containers via remote access!
Getting started with Windsurf Wave 12👇
1
4
75
8,364
We’re working hard to make Windsurf both powerful and reliable for developers.
And last but not least…👇
2
1
65
6,515
We’ve redesigned the Windsurf UI to make it easier to scan and understand Cascade’s actions.
Next up: Stability improvements👇
2
1
75
7,899
Tab’s suggestions are now faster, more helpful, and less intrusive.
Next up: Refreshed UI👇
1
1
72
7,663
Hover over any symbol (variable, function, etc.) in your codebase and get a DeepWiki-powered explanation. Go to windsurf.com to get started.
Next up: Vibe and Replace👇
4
6
149
49,331
Wave 12 is here, and it’s a big one!
📚 DeepWiki-powered docs for every symbol in your codebase
🔍 Vibe and Replace
🐛 100+ bugs squashed
🎨 Brand new UI
… and more!
Everything that’s new 🧵
94
104
970
375,357
Build with GPT-5, gpt-oss-120b, Opus 4.1, and other new models at @cognition's Applied AI Hackathon in SF on Sunday.
Hackers will get free API credits from @OpenAI, @AnthropicAI, @cerebras, and @modal_labs, as well as free access to Windsurf Pro and Devin.
Sign up 👇
20
23
211
191,005
GPT-5 is now available in Windsurf! Free for a limited time.
Based on our internal evals, which measure model performance on real-world engineering tasks, it is SOTA.
Let us know what you think!
69
55
617
756,549
Just added gpt-oss-120b to Windsurf at
0.25x credits!
Let us know how it compares to other open source models.
41
27
458
454,853
"Every engineer uses Windsurf now, and maybe triples their productivity."
In startups, speed and tooling means everything for bringing your ideas to life and securing your first customers.
From @ycombinator startups like @getathenahq to huge enterprises in the Fortune 100, Windsurf is built to help you accelerate forward.
21
16
258
36,283
Qwen3-Coder at ~2000 tokens/sec is now live in Windsurf! ⚡️
Fully hosted on US servers by @cerebras.
Video is 1x speed.
112
101
1,071
780,433
Windsurf events were great, but our joint events with @cognition_labs are even better.
We just had our first joint event in Tokyo with nearly 800 signups!
Can't wait to do more of these around the world 🌎
7
10
166
20,795
Qwen3-Coder 480B Instruct is now available in Windsurf.
Hosted fully on Western servers!
66
65
914
640,925
Once the workflow is created, you can run it by simply typing the /workflow-name in the chat bar.
1
11
6,288
Think of each step of the workflow as an individual prompt that you would send to Cascade, and the workflow file as a collection of these prompts.
Be very thorough in defining the steps for your workflow! Make sure to validate that anything written by Cascade is correct.
1
3
985
There are two ways to create workflows in Windsurf:
1. Navigate to Customizations > Workflows and create a global or workspace level workflow
2. Ask Cascade to create a workflow for you
They are then defined as markdown files in the .windsurf/workflows directory.
1
5
1,176
Upcoming Community Meetups 🏄♂️:
Bangkok - July 23rd
Lisbon - July 24th
Tokyo - July 25th
Munich - July 31st
Follow our Luma calendar below to find out when Windsurf is coming to your city.
We're adding new events each week!
12
12
127
33,710
