Blink
Code-review CLI that coding agents run after every change, using Jev to check the diff near-instantly instead of an LLM reviewer.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
Blink (blink.review) is a code-review CLI meant to be run by coding agents after every change. Per the listing, Jev checks the diff almost instantly in place of a slower LLM reviewer.
It is unrelated to the ellipsis-dev blink code-search tool of the same name. Only the list summary was available here.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does this diff have a problem the agent should fix?(inferred) | yes · no |
How it works
- Agent makes a change
- Agent runs the Blink CLI
- Jev checks the diff
- Agent fixes flagged issues
Strengths
- Fast checks after every change
Caveats
- Only a list summary was available
Getting started
See https://blink.reviewAt a glance
- Type
- Article
- Runtime
- CLI
Use cases and integrations
How curated lists describe it
Code review: CLI that coding agents run after every change, with Jev checking the diff near-instantly in place of an LLM reviewer.
yibie/awesome-jev
Frequently asked questions
What does it do?
Checks diffs with Jev after each agent change.
Is it the same as ellipsis-dev/blink?
No, that is a code-search tool.
Where is it?
https://blink.review
Related projects
Automated PR review: an LLM agent finds issues, a verifier refutes them, and Jev decides how to triage, route and label.
ProjectproductionTypeScriptRust code-review gate asking Jev small typed questions about functions and tests, failing CI only on rules measured 80% right.
CLIproductionRust- CodeOtter★ 3
Self-hosted PR review platform pairing an LLM narrative with a /v1/systemone decision engine for 6 rubric scores and 8 yes/no merge gates.
Servicebeta Coding-agent hook that asks Jev one yes/no per project rule on every edit or turn and makes the agent fix any violation.
HookbetaTypeScriptClaude Code plugin sending small judgments to Jev: rule checks that block edits, verbatim compaction, subagent sizing and routing hints.
PluginbetaPythonAdvisor for coding agents: git and Stop hooks flag test tampering, secrets and skipped hooks, with optional Jev review findings.
Hookbeta