Introducing eve, an open-source agent framework
Vercel announces eve, an open-source framework for building, running, and scaling agents with minimal setup. Agents are directories of files with built-in production features including durable execution, sandboxed compute, and human-in-the-loop approvals.
is now available in public preview.eve
eve is an open-source framework for building, running, and scaling agents. An agent is just a directory of files, and production comes built in:
The smallest agent that runs is just two files, a model and a set of instructions.
Add a tool, skill, channel, or schedule by adding a file. eve picks them up at build time and wires them in for you, so there's no boilerplate to register them.
You can scaffold and start a new agent with a single command. It installs the dependencies, scaffolds the project, and starts a dev server, so you have an agent running locally in under a minute.
Or you can let your coding agent set it up for you. Give it this prompt:
And because an eve agent is an ordinary Vercel project, ships it to production unchanged, exactly as it ran on your machine.vercel deploy
eve is the framework that Vercel builds and runs its own agents on. For the full tour, read the or the , and you can follow development in the open over at .announcementdocumentationgithub.com/vercel/eve
Durable execution
Sandboxed compute
Human-in-the-loop approvals
Subagents
Evals
Source: original entry ↗