exe.dev provides Linux VMs on the internet, quickly — SSH and HTTPS in, proxied endpoints out — designed as sandboxes for agentic development. We run Claude Code sessions in exe.dev VMs with scoped GitHub access through its integration proxy, so agents work in a real environment with real tools while credentials and blast radius stay contained. This very page was authored from one.
How We Use It
- Sandboxed VMs for long-running agentic coding sessions
- Scoped GitHub access for agents via integration proxy, no raw credentials
- Instant HTTPS endpoints for previewing work-in-progress services
AI / LLM
Why this matters: Controversial, misunderstood, and overhyped though they may be, AI and LLMs are transforming industries and society. Used carefully and responsibly, they are still a valuable tool for innovation and progress. We design and deploy LLM-powered features with a focus on safety, performance, and maintainability, leveraging managed model providers and an SDK-first approach for rapid iteration. Preferred defaults: Vercel AI SDK + AI Gateway for multi-model orchestration; Anthropic and OpenAI as primary model providers.