Vercel has launched Eve, an open-source, filesystem-first framework for building, running, and scaling durable AI agents in production.

// 48d agoPRODUCT LAUNCH

Vercel has launched Eve, an open-source, filesystem-first framework for building, running, and scaling durable AI agents in production.

Vercel has introduced Eve, an open-source TypeScript framework that adopts a filesystem-first design to simplify building and scaling AI agents. By structuring agents as directories with specific files for instructions, TS tools, and configurations, Eve makes agent composition highly intuitive. The framework provides production-ready infrastructure out of the box, featuring durable execution through Vercel Workflow to persist state across sessions, isolated sandboxed compute for secure execution, and built-in tracing and observability.

// ANALYSIS

Vercel is looking to replicate the success of Next.js in the web development ecosystem by providing the de facto standard framework and infrastructure layer for AI agents.

* The filesystem-first approach offers a clean, declarative way to structure agent capabilities, instruction sets, and tools.

* Integrating durable execution via Vercel Workflow directly solves the state recovery challenges inherent in long-running agent workflows.

* Built-in sandboxed execution makes running untrusted or dynamically generated code significantly safer and easier to deploy.

// TAGS

ai-agentsframeworkverceltypescriptopen-sourcedeveloper-tools

DISCOVERED

48d ago

2026-06-18

PUBLISHED

48d ago

2026-06-18

RELEVANCE

8/ 10

AUTHOR

evilrabbit_

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

MODEL50m ago

Opus 5 Relaxes Cyber-Classifier Restrictions by 85%

Anthropic's Opus 5 release includes updated cyber-classifiers that are 85% less restrictive than Claude 3.5 Sonnet. This update significantly reduces refusals on offensive-security tasks, signaling a key shift in how AI safety guardrails are balanced against specialized utility for security professionals.

TUTORIAL1h ago

Codex Security details AI code generation risks

As rapid development via AI code generation ("vibe coding") grows increasingly popular, products created without thorough security oversight risk shipping critical vulnerabilities to production. This post presents a hands-on examination of OpenAI Codex and AI-assisted workflows, exploring common security pitfalls in machine-generated code and outlining strategies for auditing applications before release.

UPDATE2h ago

Grok Build 0.2.121 adds turn summaries, extension grouping

xAI has launched version 0.2.121 of Grok Build, bringing key developer experience updates to its workspace interface. The release introduces concise agent turn summaries directly on dashboard rows for better context tracking, alongside alphabetical grouping within the extensions modal to streamline navigation.