Vercel launches filesystem-first agent framework Eve

// 95d agoPRODUCT LAUNCH

Vercel launches filesystem-first agent framework Eve

Vercel has launched Eve, an open-source, filesystem-first framework designed to simplify building and scaling durable backend AI agents. Inspired by Next.js, Eve allows developers to define agents, tools, and configurations using simple directory structures that integrate natively with Vercel's serverless and sandboxed infrastructure.

// ANALYSIS

Vercel is applying its successful Next.js formula of convention-over-configuration to AI agents, aiming to become the default hosting and development platform for agentic applications.

* Standardizing agent structure into folders like `tools/`, `skills/`, and `channels/` drastically reduces initial setup overhead compared to low-level frameworks.

* By embedding durable execution (Vercel Workflow) and isolated runtime compute (Vercel Sandbox) natively, Vercel solves the difficult hosting and persistence challenges of long-running agents.

* The deep integration with Vercel's proprietary ecosystem provides a smooth developer experience but also introduces strong platform lock-in.

// TAGS

agentverceltypescriptweb-developmentopen-source

DISCOVERED

95d ago

2026-06-17

PUBLISHED

95d ago

2026-06-17

RELEVANCE

8/ 10

AUTHOR

rauchg

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE28m ago

DIFF launches LLM-ready DayZ script browser

DIFF (DayZ Internal File Finder) is an open-source documentation explorer and reference tool built for the DayZ modding and scripting community. Automatically generated from Bohemia Interactive's script repository across game builds, the platform catalogs thousands of Enforce Script classes, methods, fields, globals, and file structures. It enables developers to search the codebase, trace changes between updates, and contribute crowd-sourced annotations via a shared notes repository. Crucially, DIFF is designed with modern AI workflows in mind, offering structured machine-readable endpoints (`llms.txt`, `api.json`), agent integration guides, and one-click Markdown exports for feeding context directly into LLMs.

LAUNCH1h ago

TypeSafe AI opens public access to Jev

TypeSafe AI has made its flagship foundation model, Jev, generally available to all developers without a waitlist, providing new signups with $5 in free credit (~120 million tokens). Designed as a machine-native "System One" model, Jev specializes in returning typed, probabilistic decisions—such as classification, scoring, and routing—directly within software loops at higher speeds and lower token costs than standard generative LLMs.

TUTORIAL2h ago

DAIR.AI drops Jev guide and playground

DAIR.AI has published an introductory tutorial and interactive playground for Jev, TypeSafe AI's non-autoregressive "System One" decision model. Designed specifically for programmatic automation and discrete structured judgments rather than open-ended text generation, Jev evaluates inputs against developer-defined schemas and returns typed outputs paired with uncertainty probabilities in a single pass. The guide explores practical use cases including support ticket triage, model routing, agent guardrails, and smart-home command parsing, establishing the foundational concepts for an upcoming series on architecting hybrid System 1 and System 2 agent harnesses.