Dedalus Labs

Dedalus Labs delivers cloud infrastructure purpose-built for AI agents that need to run for hours, days, or continuously in production. If you have ever watched an ephemeral sandbox wipe your agent's memory the moment a session ended, this solves exactly that pain.

Every agent gets its own persistent Linux microVM on Dedalus Machines. Files, installed packages, environment variables, caches, and running processes all survive sleep and wake cycles — so your agent picks up right where it left off. Sleep is completely free: you only pay for compute while the agent is actually running, and scale-to-zero means no idle charges.

Key capabilities include a 50ms cold start, VM-level hardware isolation for safely running untrusted LLM-generated code, a persistent POSIX-compliant filesystem across sessions, and per-second billing starting at $0.0504/vCPU-hr. GPU-capable VMs are available for local model inference, so demanding workloads stay on your terms.

Integration is seamless thanks to built-in MCP (Model Context Protocol) support with a hosted marketplace of production-ready MCP servers, plus a multi-model SDK supporting Claude, GPT, Gemini, DeepSeek, Mistral, and 100+ models. For security, Dedalus Auth (DAuth) provides zero-trust, multi-tenant authentication for MCP servers.

Dedalus is designed for developers building autonomous coding agents, research agents, CRM agents, monitoring agents, and any stateful AI workflow that needs real continuity. Getting started is easy: the free tier includes a $20 sign-up credit and 50 compute hours per month, with no credit card required.

Backed by Y Combinator (S25) with $11M in seed funding from Kindred Ventures and Saga Ventures, Dedalus Labs is built to grow with your agents from prototype to production.