eve

Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.

The Open Framework for Building Agents

Getting started

This creates a new my-agent directory, installs its dependencies, initializes Git, and starts the interactive terminal UI. The generated agent uses openai/gpt-6-luna-fast with high reasoning.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to eve

Browse all
ai-cli project preview
Integrations
Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.
@ai-sdk/typesafe-ai plus experimental_evaluate; use jev-latest as an evaluation model.
Hosted typesafe-ai/jev for AI SDK evaluate calls, no TypeSafe waitlist required.
jevcore project preview
Agent tooling
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
toolgate (RiskAverseTech) project preview
Benchmarks & research
Open auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook
jev-eval-agent project preview
Benchmarks & research
Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.
clean-code-review project preview
Agent tooling
Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.
jev_stock project preview
Benchmarks & research
An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.
typesafe-3d-chess project preview
Games & simulations
3D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels.