Cosmos
Augment Code is an agentic development platform built to help engineering teams move from isolated AI coding assistants to a coordinated system of software agents. Its Cosmos platform runs software agents at scale, giving them the context, tools, environments, memory, and feedback loops they need to improve with every workflow. Cosmos works across the software development lifecycle, with reusable expert agents for authoring pull requests, reviewing changes, analyzing risk, testing updates, and helping teams build their own specialized workflows. Its PR Author can take a task description from first commit through merge, while Pair Review reviews changes alongside the author, Deep Code Review reads pull requests end to end and posts inline comments, PR Risk Analysis surfaces blast radius, security exposure, and migration risk, and Tester exercises changes end to end with results and screenshots included.
Learn more
Devin Desktop
Devin Desktop (formerly Windsurf) is an AI-powered development environment that combines a full-featured IDE with advanced coding agents in a unified workspace. Formerly known as Windsurf, the platform enables developers to manage local and cloud-based AI agents, delegate tasks, review code, and ship software without leaving their editor. Developers can use multiple coding agents simultaneously to research, write, test, debug, and improve code while maintaining full visibility into every change. Devin Desktop includes features such as agent orchestration, shared workspaces, intelligent code completion, contextual code search, and integrated review tools. The platform supports a wide range of models, extensions, language servers, and MCP integrations, allowing teams to work with their preferred tools and workflows. Devin Desktop helps engineering teams accelerate software development, improve productivity, and manage AI-assisted coding at scale.
Learn more
Isle
Isle provides managed desktop application environments for computer-use agents, with guardrails, application monitoring, and artifact checkpoints built in. Instead of giving an agent a generic machine and leaving it to manage the application itself, Isle wraps each application in the monitoring, containment, and recovery controls needed to complete real work. Environments launch with the intended software already installed, configured, and open, while health checks verify that the application itself is ready rather than simply confirming that the underlying machine is online. Developers can connect any computer-use model or agent loop using familiar screenshot, mouse, keyboard, file-transfer, and execution primitives. Artifact checkpoints protect useful progress before important actions and can be restored if something goes wrong, while recovery controls allow agents to restart applications and return to the latest safe state.
Learn more
Bevel
Bevel is a vendor-agnostic, Git-backed control plane for enterprise AI agents, where an organization’s agents, context, skills, tools, permissions, and identities are defined as files the company owns in its own infrastructure and served to any agent runtime over MCP. Context is stored as typed knowledge nodes with provenance for every fact, including where it came from, who last changed it, and when it was verified, then compiled into a graph that can be traversed, updated, and used for dashboards. Skills are written as plain Markdown procedures that process owners can read, review in diffs, and port across runtimes. Tool manifests define available capabilities, while secrets stay in a vault and access rules determine which agents may read specific files or call endpoints. Each agent has its own identity, credentials, and scope so actions remain attributable.
Learn more
