@rauchg: Make the model a cog in a machine you own. AI SDK → open model API http://Eve.dev → open Agent API AI Gateway → open ZD…
Summary
Eve is a new open-source framework for building durable, self-hosted AI agents, inspired by Next.js, emphasizing data ownership and production-ready features like sandboxing, human-in-the-loop, and evals.
View Cached Full Text
Cached at: 07/12/26, 07:00 PM
Make the model a cog in a machine you own.
◾ AI SDK → open model API ◾ https://t.co/O7y9dmUqk5 → open Agent API ◾ AI Gateway → open ZDR inference
Startups and enterprises must own their data, evals, model choices, software layer. Don’t outsource your brain.
eve
Source: https://eve.dev/
The framework for building agents
Like Next.js for agents. Build durable agents with one folder.
$npx eve@latest init my-agent
Works natively with Next.js
Wrap your config withwithEve()and the agent mounts into your existing app. Same dev server, same deploy.useEveAgent()finds its routes on its own, so there’s no CORS to configure and no URL env vars to keep in sync.
Built on open-source SDKs, yours to self-host
Swap any backend and self-host the whole runtime, with zero managed-infrastructure dependencies.
You can deploy anywhere. Postgres-backed durability, Docker sandbox, Ansible deploy, zero managed services.See the example
Everything you need for production agents
Durability, sandboxing, human-in-the-loop, and evals are built into the framework. Focus on building your agent.
- Workflows survive crashes and restarts. Every step is checkpointed. Agents park when waiting, resume on the next message.
- Agents run code in isolated sandboxes. File system access, bash execution, and code, all fully isolated.
- One agent codebase deploys to web chat, Slack, API, cron, CLI, and custom apps.
- Tools that need confirmation trigger approval gates. Sessions park until resolved, then resume seamlessly.
- Delegate specialized work to child agents with their own prompts, tools, and sandbox.
- Define test suites with scoring rubrics. Run evals on every deployment and on a schedule.
Build your first agent today.
Similar Articles
@rauchg: Agents are particularly hard-to-debug software. For one, and by design, AI models behave in non-deterministic ways. Eve…
Vercel launched Eve, an agent framework with built-in observability, debugging, durable execution, and sandboxed compute, aiming to simplify production agent development.
@rauchg: Agentic self-improvement. Give your agent the ability to introspect its past runs, spot inefficiencies, errors, redunda…
Eve is a framework for building durable, production-ready AI agents with built-in observability, introspection, and self-improvement capabilities, designed to work seamlessly with Next.js and Vercel deployments.
@rauchg: The filesystem is beautiful. Want your http://eve.dev agent to have GitHub powers? Define 𝚝𝚘𝚘𝚕𝚜/𝚐𝚒𝚝𝚑𝚞𝚋.𝚝𝚜 …
Vercel's Guillermo Rauch announces Eve, a framework for building durable AI agents with GitHub integration, featuring sandboxing, human-in-the-loop, and open-source self-hosting.
@rauchg: eve evals itself with 𝚎𝚟𝚎 𝚎𝚟𝚊𝚕. Web frameworks made testing an ecosystem choice. e.g.: React didn’t ship with a …
eve now ships with built-in eval capabilities for agents, addressing the need for first-class testing in AI agent development.
@omarsar0: https://x.com/omarsar0/status/2070884837372703196
Vercel released Eve, an open-source framework for building and scaling AI agents using a filesystem-first approach, treating agents as directories of files. The framework provides durable sessions, sandboxing, approvals, tracing, and evals out of the box.