DDharundp6Benchmarks & research

jev-carryforward

What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation model via Vercel AI Gateway.

Explore repositoryVisit website

How it uses Jev

An MCP server with two tools. record saves a fact the moment it happens. recall brings those facts back when you start a task, and uses Jev to keep only the ones that matter right now.

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 jev-carryforward

Browse all
typesafe-ai-benchmark project preview

typesafe-ai-benchmark

Benchmarks & research
This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.
IMade byiammrduncan38
jev-web-analyzer project preview

jev-web-analyzer

Benchmarks & research
See what Jev thinks about your SaaS website — powered by ReplyNodes web context and Vercel AI Gateway.
RMade byreplynodes3
jevalyzer project preview

jevalyzer

Benchmarks & research
Grade the agent sessions already on your disk. Claude Code, Codex, opencode, Gemini CLI and Antigravity, scored with Jev for cents.
KMade bykillerz32
jev-model-router project preview

jev-model-router

Agent tooling
Jev (TypeSafe) model router on the Vercel AI Gateway
AMade byaz97132
jev-skillful project preview

jev-skillful

Agent tooling
Per-prompt capability router for coding agents: resolves installed skills, MCP servers, agents and commands against your prompt via TypeSafe Jev, and measures whether the injection actually helps.
BMade bybestagentkits2
clear-head project preview

clear-head

Agent tooling
Claude Code Stop hook that checks an AI assistant's claims against what it actually read this session, using TypeSafe's Jev as the judge
VMade byVladyslavHontar2
jev-dev project preview

jev-dev

Demos & playgrounds
同じ発言を jev と LLM の両方に判定させ、感情の変動値のズレと応答速度を1画面で見比べるデモ（affectus + Vercel AI Gateway）
NMade byn-yokomachi0
ai-cli project preview

ai-cli

Integrations
Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.
VMade byvercel-labs813
eve project preview

eve

Integrations
Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.
VMade byvercel5.3k