Today we're open sourcing https://t.co/p76KVdY7dG, a reference platform for cloud coding agents. You've heard that companies like Stripe (Minions), Ramp (Inspect), Spotify (Honk), Block (Goose), and others are building their own "AI software factories". Why? 1️⃣ On a technical level, off-the-shelf coding agents don't perform well with huge monorepos, don't have your institutional knowledge, integrations, and custom workflows. 2️⃣ On a business level, the moat of software companies will shift from 'the code they wrote', to the 'means of production' of that code. The alpha is in your factory. Open Agents deploys to our agentic infrastructure: Fluid for running the agent's brain, Workflow for its long-running durability, Sandbox for secure code execution, AI Gateway for multi-model tokens. (Because of our focus on Open SDKs and runtimes, this codebase is a gem even if you're not hosting on Vercel.) TL;DR: if you're building an internal or user-facing agentic coding platform, deploy this: https://t.co/xdsc42nbDN
Guillermo Rauch Launches Open Agents to Build Custom AI Software Factories
Vercel· Updated
Guillermo Rauch, CEO of Vercel, open-sourced Open Agents as a reference platform for building autonomous cloud coding agents. The release provides the infrastructure for companies to build internal software factories that integrate private institutional knowledge and custom workflows. This shifts the competitive advantage from the code a company owns to the efficiency of the system that produces it.
Fluid for compute and Workflow SDK for durable agent loops (iterative cycles that can resume after failures).Off-the-shelf coding agents often struggle with massive monorepos and lack the institutional knowledge required for complex enterprise environments. This release provides a blueprint for AI software factories, allowing companies to build custom systems that understand their specific integrations, private context, and internal development workflows.
You can deploy the template to access secure cloud sandboxes for code execution and an AI Gateway for routing. The system uses an explorer and executor subagent pattern to handle parallel tasks. The codebase is available as an open-source repository for building internal agentic platforms that ship code autonomously.
Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →





