TL;DR:

We’re excited to launch Dedalus Labs, an AI-native cloud platform for developers to build agentic AI applications. Our SDKs allows you to connect any LLM to any MCP servers – local or remotely hosted by us. No Docker files or YAML configs required.

• Blog: https://dedaluslabs.ai/blog/dedalus-seed-round
• Product Demos:
  • https://www.youtube.com/watch?v=s2khf1Monho
  • https://www.youtube.com/watch?v=4B1xuRCgLgA

The Problem: Building Agents Is Hard

Building tool-using agents ≠ calling v1/chat/completions.

Today, developers are still stuck with:

• Running their MCP servers locally.
• If deploying remotely, wiring up AWS and config hell.
• Juggling model quirks, streaming issues, and auth across GPT-4o, Claude 3.5, Sonnet, Flash, etc. (♾️ API keys).
• Rebuilding everything just to add a new tool.

We were tired of writing hundreds of lines of code and battling Docker files and infra—all for a spaghetti agent that breaks under stress.

So, we built the tool we wished existed.

What We Offer: Complex Agents in 5 Lines of Code

Dedalus invented the simplest way to build and deploy agents—a drop-in infrastructure layer that unifies models, tools, and orchestration.

Our open-source SDK supports:

• Vendor-agnostic model handoffs
• Chaining both local tools and hosted MCPs
• Real-time streaming across any provider

—all in 5 lines of code.

And our managed infra lets you deploy an MCP server in 3 clicks, so anyone can equip their agent with tools. No Docker files, no setup.

Why MCP: Tools Made for Agents

MCP (Model Context Protocol) is becoming the standard for how models talk to tools. Think of it as an API that AI models already know how to call—reliable, predictable, and language-agnostic.

As more companies adopt MCP, exposing your product as an MCP server means you’re not just serving humans anymore—you’re serving agents.

We’re building the infrastructure that powers that shift.

Our Story: Two Princeton CS Students with High Standards

We’re Cathy (ex-Voyage AI / Salesforce) and Windsor (ex-DeepMind / Sentient AGI).

We first ran into this problem while working with MCP during Windsor’s time at Sentient AGI. Every solution felt wrong: drag-and-drop GUIs, brittle configs, frameworks that broke under real workloads. Nothing met our standards for what good developer infrastructure should be.

So we built what we always wanted—a developer-first platform that makes agentic workflows composable, scalable, and effortless to ship.

If no one else is going to build it right, we will.

Get Started + Early YC Deal

• Quick install: pip install dedalus-labs
• Docs: docs.dedaluslabs.ai
• YC Deal: we’re giving $200 free credits to every YC company. Email founders@dedaluslabs.ai to claim your deal!

Let us build your wings so your agents can fly. 🪽