Codeium

* Product * Solutions * Customers * Resources * Pricing Contact salesLog inDownload # Devin Desktop Manage fleets of local and cloud agents from one surface. Plan, delegate, review, and ship without leaving your editor. Download for MacOS THE HOME FOR EVERY AGENT YOU RUN LEARN MORE → Agent Editor New session Sessions Spaces Widen the model hidden dimension Working... Switch the MLP activation to GELU 42m ago• Learning rate tuning Increase the Muon matrix learning rate Working... Add a learning rate warmup phase PR is ready• Tune the WSD warmdown ratio Waiting for CI• Establish the training baseline 3h ago• Add QK-norm and value embeddings 1h ago• Sessions Board List Display Status Space Pull request Agent Clear filters Running2 Widen the model hidden dimension Working... Learning rate tuning Increase the Muon matrix learning rate Working... Waiting for review2 Learning rate tuning Add a learning rate warmup phase PR is ready• Learning rate tuning Tune the WSD warmdown ratio Waiting for CI• Done3 Switch the MLP activation to GELU 42m ago• Establish the training baseline 3h ago• Add QK-norm and value embeddings 1h ago• main Launchpad 0 0 Screen Reader Optimized Ln 231, Col 29 Spaces: 2 UTF-8 { } TypeScript JSX Cognition Platform (Enterprise) Windsurf - Settings Agent Command Center ## A team of agents for every engineer. Devin Desktop is the home for coding agents to do *your* best work. You decide what to build, then your agents write the code, chase the edge cases, and test every detail. autoresearch Establish the training baseline Add QK-norm and value embeddings A world-class IDE ## The power of an IDE, exactly when you need it. Read, trace, and debug every change your agents ship. Devin Desktop includes a full IDE with syntax highlighting, autocomplete, and debugging tools built in for you to stay in flow. autoresearch train.py 116 ``` self.mlp = MLP(config) ``` 117 118 ``` def forward(self, x, ve, cos_sin, window_size): ``` 119 ``` x = x + self.attn(norm(x), ve, cos_sin, window_size) ``` 120 ``` x = x + self.mlp(norm(x)) ``` 121 ``` return x ``` 122 123 124 ``` class GPT(nn.Module): ``` 125 ``` def __init__(self, config): ``` 126 ``` super().__init__() ``` 127 ``` self.config = config ``` 128 ``` self.window_sizes = self._compute_window_sizes(config) ``` 129 ``` self.transformer = nn.ModuleDict({ ``` 130 ``` "wte": nn.Embedding(config.vocab_size, config.n_embd), ``` 131 ``` "h": nn.ModuleList([Block(config, i) for i in range(config.n_layer)]), ``` 132 ``` }) ``` 133 ``` self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False) ``` 134 ``` self.resid_lambdas = nn.Parameter(torch.ones(config.n_layer)) ``` 135 ``` self.x0_lambdas = nn.Parameter(torch.zeros(config.n_layer)) ``` 136 ``` # Value embeddings ``` 137 ``` head_dim = config.n_embd // config.n_head ``` 138 ``` kv_dim = config.n_kv_head * head_dim ``` Agent Client Protocol ## All the models, All the agents. Work across models and agents, powered by the Agent Client Protocol (ACP). micrograd Implement backprop implement backprop from scratch — a minimal scalar autograd engine, like micrograd I'll build a single `Value` type that records the computation graph as expressions run, then backpropagates with reverse-mode autodiff. Starting from an empty repo with the node scaffold — the data, its gradient, and the edges to its parents. engine.py+9 Each forward op returns a new `Value` and stashes a local `\_backward` closure — the chain rule for that op, pushing the output gradient into its inputs. engine.py+17 engine.py+13 Now the backward pass itself: topologically order the graph from the output, seed its gradient to 1, and run the stored closures in reverse so each node is fully accumulated before its parents are reached. engine.py+12 Sanity-checking the gradients against PyTorch on a small expression with a reused variable, so the accumulation is actually exercised. test\_engine.py+9 python -m pytest test\_engine.py -q Done — a ~50-line autograd engine, written from scratch. `backward()` topo-sorts the graph and applies each op’s local gradient in reverse, accumulating with `+=` so reused sub-expressions sum correctly. The gradient check matches PyTorch to 1e-6. Code SWE-1.6 Fast Devin Local AgentsDevin CloudDevin LocalCodexClaude AgentOpenCodeCascade Local micrograd Spaces Spaces Onboarding Flow Redesign feat/onboarding-flow-design Build onboarding UI Working… Update onboarding API endpoints Working…• Fix authentication error 12m ago• Improve Unicode normalization Waiting for approval• Implement UTF-8 encoding 2d ago• ### One Space for every agent Use Spaces to share context and Git worktrees across all your agents. Supercomplete ### Tab, Tab, Ship Supercomplete predicts your next thought, not just your next edit. ## Agents on ACP Fast ContextWhere is reconciliation scheduled? ### Instant codebase context Fast Context finds the exact files and lines your agent needs—in milliseconds. 1 Bug setFakeTimerMarker sets clock to false instead of resetting itBug FakeTimers.zig:188 3 Flags Mark all as read Test order dependency - first test assumes clean stateInvestigate 25869.test.ts:20-23setFakeTimerMarker silently ignores errorsInformational FakeTimers.zig:179-189Comment at line 185-187 is inconsistent with implementationInformational FakeTimers.zig:185-187 ### Never miss a detail Rapidly (or deeply) review every agent diff—before you push. ### Free world-class models Unlimited access to SWE-1.6, the fastest coding model in the world. plan.md To build a dashboard for real-time store sales data, we will stream events from Kafka over websockets and render them onto a three.js globe. View planImplement in Cloud ### Effortless handoff to the cloud The only IDE designed for you to close your laptop. Customers ## Teams building with Devin Desktop > Devin Desktop makes it easy to dispatch and monitor our array of agents from a single command center. We're excited to partner with Cognition to bring the agents Ramp engineers already use into one shared workspace, making it easier to jump between tasks, preserve context, and get more done. Shaiyon HaririResearch Engineer > At Harvey, we built our internal background agent, Spectre, to work across long-running engineering efforts while carrying organizational context for our legal research, engineering, product, and design teams to seamlessly collaborate. With Devin Desktop's support for custom background agents, that context now extends to every engineer's laptop, so humans and agents work from the same shared understanding instead of starting from scratch. Joey WangEngineering Lead > NVIDIA is joining Cognition's research preview for multi-agent support in Devin Desktop. Our engineers run multiple agents across complex workflows every day, and we're excited to help define how they share context and coordinate in one place. Subhash RanjanEngineering Lead - AI Tools > We've been working closely with Cognition as a design partner on multi-agent support in Devin Desktop. Our engineers run multiple agents every day and Devin Desktop is the first tool that lets them manage all of them together, with shared context, from one place. Rahul ChalamalaMember of Technical Staff > Devin Desktop gives our teams the same intelligent agent experience, but with the full permissions and flexibility of their local machines. For development work that benefits from a faster, more hands-on environment, it's a natural fit. It's snappier, it's accessible, and it fits the way a lot of our developers are working today. Ciprian NechitaSenior IT Architect ## Make Devin Desktop your own Extend Devin with the tools, skills, and plugins your team already uses. Slack MCP Server Search channels and messages, send and read messages, and access user profiles. ESLint Extension Find and fix problems in your JavaScript and TypeScript code. Linear MCP Server List, create, update, and query issues, projects, initiatives, cycles, and comments. rust-analyzer Language Server Code completion, go-to-definition, and inline diagnostics for Rust. Notion MCP Server Retrieve and manage pages, databases, and comments; search across your workspace. Prettier Extension Opinionated code formatter that enforces a consistent style across your codebase. Figma MCP Server Get files, nodes, and images; manage comments, components, styles, and webhooks. clangd Language Server C and C++ language server with completion, navigation, and diagnostics. Sentry MCP Server Retrieve issue data and stack traces; search, filter, and update issue status. Windsurf Pyright Extension Fast type checking, IntelliSense, and diagnostics for Python. Stripe MCP Server Create and manage customers, products, subscriptions, invoices, payouts, and refunds. gopls Language Server The official Go language server for completion, navigation, and refactoring. Vercel MCP Server Manage projects and deployments, analyze logs, and search Vercel documentation. Datadog MCP Server Retrieve telemetry insights and manage incidents, monitors, logs, dashboards, and traces. Atlassian MCP Server Access Jira and Confluence — manage issues and create enterprise documentation. ## So good you can't work without it Download for MacOSRequest a demo → PRICING OVERVIEW ## Learn about our plans Free $0 Download ProPOPULAR $20per month Select plan MaxNEW $200per month Select plan Teams $80/mo + $40/mo per full seat Select plan Enterprise Let's talk Contact us STATS ## Trusted by developers. 1M+ UsersTrusted by over a million developers worldwide 4000+ Enterprise CustomersStartups, agencies, and enterprises ## Frequently Asked Questions What is Devin Desktop? Devin Desktop is the new name for Windsurf. We’re building on the IDE foundation of Windsurf to introduce the command center for managing all your agents in one place. The Agent Command Center (Spaces, Kanban view, and multi-agent management) is front and center, while the full IDE experience you know remains fully accessible. Read the announcement → How do I upgrade to Devin Desktop from Windsurf? Devin Desktop arrives as a standard over-the-air update, so your plan, pricing, extensions, and settings all carry over automatically. You can also download the latest Devin Desktop version from the download page. Will I lose anything if I update? The IDE, your extensions, workflows, settings, and in-progress work will all remain intact and will be fully migrated when you update. Only the name and branding are changing. Learn more in the docs → Does my plan or pricing change? No. Your current plan and pricing stay exactly the same, including legacy Windsurf Enterprise plans. Learn more in the docs → What is happening to JetBrains support? Windsurf for JetBrains (IntelliJ IDEA, PyCharm, WebStorm, and more) continues to be available for download. Get Windsurf for JetBrains → Privacy PolicyTerms of ServiceYour Privacy Choices LinkedInX (Twitter)