Skip to content
JevDirectory.org
CommunityRepos & SDKs5.3k starsVerified 2026-09-22

eve

A filesystem-first framework for durable AI agents whose auto model router defaults to Jev through Vercel AI Gateway and whose evaluate helper asks typed Choice, Score, and Boolean questions inside tools.

Open github.comvercel/eve
Category
Repos & SDKs
Published by
Community
Author
vercel
Added
2026-09-22
Tagscommunitytypescriptagentsvercelsdk

Highlights

  • Agents are directories: instructions.md is required, while tools, skills, channels, and schedules are optional folders discovered by convention.
  • npx eve@latest init my-agent scaffolds a project, installs dependencies, initializes Git, and starts the interactive terminal UI.
  • The published package includes its full documentation, so coding agents can read it locally from node_modules/eve/docs.
  • Tools are typed functions built with defineTool and a zod inputSchema, and the model is chosen in agent/agent.ts with a Gateway model ID.
  • Its auto model router defaults to Jev through Vercel AI Gateway, and evaluate asks typed Choice, Score, and Boolean questions inside tools.

Quickstart

bash
npx eve@latest init my-agent
cd my-agent
npm run dev

Watch out

Apache-2.0 and in beta under Vercel's public beta terms, so APIs may change. Needs Node.js and npm; the AI SDK evaluation model specification is experimental, and the caller owns routing and effects.

More like this

NeuroLink
137GitHub stars
A Juspay TypeScript SDK that treats Jev as a third inference type beside generate and stream: providers declare which kinds they serve, and tryDecide returns typed boolean, choice, or score answers, null when no decision provider is set.
Repos & SDKs#community#typescript#sdk
Communityneurolink
pi-typesafe
41GitHub stars
A Pi extension and library that gives the agent and other extensions one consented, key-managed Jev client, with a batched typesafe_evaluate tool for classify, triage, compare, and score judgments.
Repos & SDKs#community#typescript#sdk
Communitypi-typesafe
json-render
18kGitHub stars
Generative UI framework with an experimental Jev composer that selects components and layout from application-supplied candidates through Vercel AI Gateway, rendering catalog-constrained JSON specs.
Repos & SDKs#community#typescript#vercel
Communityjson-render
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Fast browser use with Stagehand

Kyle Jeong
Kyle Jeong
Browserbase
@kylejeong
·

we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 30 replies

LLM-as-a-judge, sped up

Yuchen Jin
Yuchen Jin
Databricks
@Yuchenj_UW
·

Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)

Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 94 replies

Instant compaction with Jev

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be  Show more

Image
Image
tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Watch on X
Reply
Read 164 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply
Read 137 replies

Jev lands on OpenRouter