Jev directory
CommunityJev Tools & CLIs
blink.review — AI Code Review
Blink enforces your team style guide, like AGENTS.md, by checking every file edit made by Claude Code and Codex and handing findings back to the agent inside the session in under half a second; it is mostly powered by Jev. Free public beta.
- Reading time
- 3 min
- Published by
- Community
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Platforms
- CLI
Highlights
- Runs after each agent turn: blink reviews the edit and hands findings back in under half a second, and the agent fixes them before you see them.
- Mostly powered by Jev from typesafe.ai; the FAQ contrasts Jev's nearly instant outputs with LLM latency.
- Setup is blink setup for your agent; it is a CLI tool, so any agent can use it.
- Checks edits against team style rules such as AGENTS.md and notifies the agent inside the session when a rule breaks.
- Free for individuals while the product is in a free public beta.
Watch out
Grounded on the site text captured on 2026-10-15; the page names Jev as the main engine and states sub-half-second review but gives no accuracy figures, no licence, and no repository detail beyond a GitHub install link. The site offers a live demo and a playground, but neither was exercised for this entry.
Questions about this entry
Short answers drawn from the linked project or page.
An AI code review layer for coding agents with the tagline make your coding agents behave. It enforces your team style guide, like AGENTS.md, by checking every file edit made by Claude Code and Codex and notifying the agent inside the session if a change breaks a rule.
The site's FAQ says blink is mostly powered by Jev from typesafe.ai, and contrasts Jev's nearly instant outputs with LLM latency. That speed is what lets it run after every code change an agent makes rather than as an occasional review.
Run blink setup for your agent, per the site. Blink then runs after each of the agent's turns: the agent edits a file, blink reviews the change and hands the findings back in under half a second, and the agent fixes the issue before you see it. The site links install instructions on GitHub.
All of them, according to the FAQ: blink is a CLI tool designed to be used by any agent after every code change, and the how-it-works section names Claude Code and Codex as the agents whose edits it checks.
Under half a second per change, the site says, and the Jev FAQ adds that Jev's outputs are nearly instant compared with LLMs. No benchmarks or accuracy figures appear on the captured page.
Nothing for individuals while the product is in a free public beta, per the site. No paid tier or enterprise pricing is described in the capture.
The site positions it as an in-session enforcement layer for agent edits against your style rules, with findings handed back to the agent rather than filed on a pull request. The capture shows a live demo and playground but makes no claim about catching every issue.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Thread on Selmar's Jev code-review calibration notes and ordering.py comparisons.
Lectem2 pointsCalibrating Jev as a Code ReviewerRead the thread on Hacker NewsHacker News: Jev classifies agent PR hunks as P0, P1, or P2 so reviewers see P0 first.
namanbhulawat47 pointsJev Based Code ReviewRead the thread on Hacker NewsX: Magic Jev Ball for code review
X: jev-review: a local-first score loop for coding agents
More Jev resources like this
A linter whose rules are plain-English yes/no questions about code — secrets in logs, retry loops that run forever, leaked error messages — answered by TypeSafe's Jev as calibrated probabilities, with output shaped like any other linter.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
ice-hazymoon/jevlintTypeScript
ice-hazymoon/jevlintTypeScriptA Rust CLI that reviews Git diffs and source scans as fast, staged judgments with concrete evidence, severity and owner routing, powered by TypeSafe Jev through a thin HTTP client speaking the system_one wire format.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
brianluby/momus-reviewRust
brianluby/momus-reviewRustRuns cheap Jev checks beside a Claude coding session: code rule lint against project rules, doc consistency checks, and context retrieval, re-checking only changed code and recording every verdict so it is not paid for twice.
Jev Tools & CLIs#community#catalog-import#logicrw
Latitude is an open-source observability platform for AI agents: one line of telemetry captures traces, failing traces group into tracked signals, and fixes are dispatched to coding agents and replayed against real traces.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
latitude-dev/latitude-llmTypeScript
latitude-dev/latitude-llmTypeScriptAn enterprise admin-console test tool that generates replayable Excel test cases from live browser pages, or replays existing Excel cases, driving Playwright with local Laya or a compatible decision API to match fields, options, and targets.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
anthonyli/laya-pilotJavaScript
anthonyli/laya-pilotJavaScriptFuzzy linter hook for Claude Code and Codex: after the agent edits a file, it sends the added code to Jev, which answers Noul checks against team rule packs in about 0.3 seconds, letting the agent fix violations before code review.
Jev Tools & CLIs#community#linter#claude-code
Community
ckorhonen/jev-lintHTML
ckorhonen/jev-lintHTMLFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.