CrossCheck
Your team's code review rules, enforced on every PR
What it does
AI writes code faster than anyone can review it. Generic AI reviewers just nitpick style, the rules that matter (migration safety, API conventions, logging, ownership) live in your seniors' heads. CrossCheck turns those rules into pass/fail checks. Write them in plain English; we run them on every PR with line-numbered evidence. No CI to maintain, no LLM keys to manage. Humans set the bar. AI runs the checks. Free for 7 days.
Does the same job
all alternatives →


- OSOpen-source CI for coding with AIFeb 2026 · github.com · ▲6
Blog post: https://spencerburleigh.com/blog/2026/02/13/crosscheck/ Repo: https://github.com/sburl/CrossCheck
- VLVibecheck – lint for AI-generated code smells (JS/TS/Python)Mar 2026 · github.com · ▲7
I built a CLI that detects patterns AI coding tools leave behind: empty catch blocks, hardcoded secrets, as any everywhere, comments that restate the code, god functions, SQL concatenation. 24 rules across JS/TS and Python. Zero config, runs offline, regex-based so it's fast. npx @yuvrajangadsingh/vibecheck . Also ships as a GitHub Action for inline PR annotations and standalone binaries (no Node required). Why: CodeRabbit found AI-generated PRs have 1.7x more issues than human PRs. Veracode says 45% of AI code samples have security vulnerabilities. "Vibe coding" is everywhere now…
More dev tools this month
the category →



Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com

OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com

Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai


- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com