Benchmark for silent omissions in AI coding-agent patches: 310 labeled instances from 8 Python libraries, a deterministic AST detector, 4 LLM/probabilistic judges, pre-registered rules and paired cluster-bootstrap CIs. Includes the results that went against the thesis.
Coding agents & review — page 8
Coding assistants, IDE plugins and review tools that use Jev to gate edits, choose the next step or judge a diff.
292 active projects match this task, ordered by traction.
A coding agent you talk to in Slack, powered by an OpenCode v2 server
The missing GUI for Claude Code - local-first dashboard for sessions, tokens, context windows, memory, skills, hooks, and MCP servers. Zero config, reads ~/.claude directly.
1
Keep Claude Code as your architect and route the token-heavy typing to a local GPU or a cheap API tier -- without leaving your session.
Claude Code hook: loose chat messages become a structured prompt map in your own words (goal, constraints, done criteria, questions). Judged by Jev, never blocks.
Claude thinks, jev clicks: a two-way loop between Claude Code and jev-ultrafast. 5-6x faster browser tasks, with before/after benchmarks.
Claude Code hook: Jev (TypeSafe) auto-approves read-only shell commands in milliseconds. Everything else still asks you.
Jev judges every review and return, Elasticsearch aggregates the judgments, and a leashed Claude Code agent turns them into proposed catalog fixes that a person approves.
No project description available.
Picks the reasoning effort for each turn of Claude Code with a System One classifier
0
Claude Code plugin: Jev (TypeSafe) checks Claude's plan against your request before it builds, and its final summary before it stops; gaps go back to Claude until Jev passes it.
Watchdog for AI coding agents: stops Codex/OpenCode when they loop, stall or drift off task, then resumes the same session with a correction. Built for Claude Code orchestrators. Uses Jev via OpenRouter.
0
Kit gratuito para probar Jev (TypeSafe) con tus datos: clasificador, test de indexación, las pruebas del vídeo y habilidad para Claude Code. Por Centry.
A work ledger for coding agents that verifies what they report. Plans, tasks, claims and handoffs live in SQLite, and a Jev-compatible judgment model checks briefs, done reports and replies against them. Runs as a Claude Code and Codex plugin, with hosted Jev, open Jev servers, Laya or Jev-Style as the judge.
Claude Code: Jev tool gate + Anthropic-compatible proxy (route + trim→compress)
Per-turn reasoning effort for coding agents, classified by TypeSafe's Jev via AI SDK (Vercel AI Gateway / OpenRouter / TypeSafe). Claude Code plugin; Codex, Cursor, Amp next.
Reference coding agent wiring Jev (System One) and Opus 5.5 (System Two)
A code review check that learns from reviewer rulings without fine-tuning. Jev (TypeSafe AI) judges each diff hunk against your team's guidelines; a Meko datapack (powered by YugabyteDB) holds the guidelines, the rulings, and a trace of every decision. Companion repo for the blog post "Jev and Meko Make Code Review Feedback Stick".
Agente de browser para o Claude Code: jev-ultrafast + Jev (TypeSafe) com guardas de domínio, paragem antes de ações irreversíveis, verificação do resultado e custo por tarefa.
Claude Code skill: find searches where Google shows the wrong one of your pages, from Search Console, judged by TypeSafe's Jev model. Under 1 cent per run.
Claude Code skill: see how ChatGPT treats your brand across real buyer questions, read by TypeSafe's Jev model. About $0.20 per run.
Jev-guided transcript compaction for Claude Code. Rust rewrite of tamaratran/fast-jev-compaction.
Claude Code plugin: per-prompt reasoning-effort routing with TypeSafe Jev
Jev (TypeSafe) as the decision layer for Claude Code: permission gate, skill routing, conditional instructions, effort-tiered subagents, context packs. Tested PoC with evals.