jev-rerank-bench: Can a decision model beat

The Android assistant reads visible conversations through accessibility and local OCR, displaying analysis and reply suggestions in an overlay. Jev judges intent and response choices; a generative model drafts three candidates and Jev ranks them.

The pipeline develops a learning brief, mathematics, visual plan and Manim scene, then reviews the rendered result. Jev evaluates candidate artifacts and Astra's text audits through typed Score, Noul and Choice answers; it does not receive the images.

The bot replaces post-only limit quotes on Monad blocks and streams book, order and fill events to a dashboard. With MODEL=jev and TYPESAFE_AI_API_KEY, Jev chooses buy or sell; the default mock model is a momentum heuristic.

JevChat-Windows reads WeChat and KakaoTalk conversations with local OCR and offers candidate replies beside the chat window. Jev judges intent and tension and ranks three candidates; a separate language model drafts them. Configure a decision-provider key and a drafting-provider key on Windows 10 1903+ or Windows 11.

Jev Search turns plain-language requests into web links and snippets with editable filters and visible relevance scores. For local use, configure Search1API and a Jev provider in .dev.vars, install dependencies with pnpm, and run pnpm dev.

The library identifies IRS forms and page kinds from extracted text using a JSON registry of form descriptions. Use classifyPage with text lines, jevBackend and criteria.json. PDF helpers additionally require Poppler; the backend needs a TypeSafe key.

Instructions, tools, skills, channels and schedules live in conventional directories, making an agent project inspectable and extensible. The evaluate helper sends typed questions about supplied state through eve's model authentication, defaulting to Jev.

The native CLI supports an interactive shell, scripted requests and embedding, with skills, MCP servers and subagents. Jev receives review policy, context and the pending action, returning a clear or caution decision for the permission pipeline.

The platform supports developing and evaluating SRE agents against live system environments containing operational failure scenarios. Jev support is disabled by default; when enabled for Codex, it reviews diagnostic tests and submissions from evidence sent to TypeSafe.

No project description available.

🚀 Feather Wand - JMeter Agent for performance engineers w/ Codex and Claude Code integration

Agent orchestration that guides projects toward demonstrable goals.