Developer Tools5 days ago
Odd Eye — Understand your code before asking AI to fix it
Understand code flow and app connections before asking AI to help modify your app.
@minmuner_devlog · X
Thanks for the feedback; I’m open to anything.
The full gallery
Tech stack
22 projects
Understand code flow and app connections before asking AI to help modify your app.
@minmuner_devlog · X
Thanks for the feedback; I’m open to anything.
Detects AI agent runaway loops and generates verified fix PRs for GitHub or local apply.
@void_rags · X
Introducing Orqis AI, an AI Watchdog that also fixes Agents. Have a look:
Notes with code blocks, Kanban bug tracker, and snippet library with GitHub import.
@SinghApurv1711 · X
Hey! Check it out here:
Identify insects and bugs by uploading photos for instant AI analysis.
@buildwithahsan · X
Just launched an AI Bug Identifier 🐞 Upload a photo and identify bugs and insects instantly using AI. Building in public and learning every day 🚀 🌐 #AI #BuildInPublic #WebDevelopment
Runs real exploits against your web apps, APIs, and AI features with proof of each finding.
@yedil_bek · X
Building RedRun - security testing that proves what it finds. Runs the real exploit + hands you the exact request/response: SQLi, IDOR, SSRF, XSS, JWT + AI prompt-injection. Zero false positives. Free scan → Active engine invite-only - DM for access code
Secure AI agent actions with code checks, permission gates, and approval workflows.
@RElharrak39428 · X
Playable collection of small, absurd AI projects, each taking about ten seconds
@KarolBuilds · X
My AI slop at is so underrated that I’m the only visitor.
Scans live web apps for security vulnerabilities like exposed keys and open databases in 60 seconds.
@guhanvenkaty · X
Tako's free preview is live: Paste your URL, get a security verdict on your vibe-coded app in 60s. Not an AI wrapper: it fires real requests and PROVES exposure, pulling data from your open DB with no login. Scanning puts you on the early-access waitlist.
Compare git, Jujutsu, and GitButler performance on coding tasks with Claude Code and Codex agents.
videlov · HN
I was interested in answering this question so I built a benchmark comparing git, jj and gitbutler in agentic context https://vcbench.dev/ Disclaimer - I am a co-founder of GitButler
Test AI agents against replayed production traces to reproduce bugs and catch regressions.
aisinghal
Debug and monitor AI agents with real-time visualization and performance analytics.
@simranrambles
A registry of hand-crafted React components and templates for building polished UIs.
@polyqoy · X
This video shows a fully animated 3D site built in 2 minutes with claude code. one terminal command. but the prompt was almost irrelevant. the real work was the pre-load: ui/ux pro max skill, a hero component from framer motion stacked in before claude touched anything the toolkit did the job. the prompt just pulled the trigger. that's also why most people's claude output looks generic. they skip the setup and blame the model.