All activity
Andrei Kniazevleft a comment
My setup is Claude Code on a remote server, I SSH into it for all my dev work — shipped a whole product this way. Genuinely curious about voice mode though. Does it need a local machine with a mic, or can it somehow work through an SSH session? I've been dealing with garbage system dictation for months, would switch in a heartbeat.
Claude Code Voice ModeSpeak your prompts into Claude Code
Andrei Kniazevleft a comment
WordPress had millions of sites before anyone had Wordfence. Security tooling showed up late — same thing is happening with vibe coding, just faster. I wanted to see how bad it actually is, so I scanned 100 vibe-coded projects. 65% had security problems hiding behind a perfectly working UI. A lot of people ask their AI about security while building. Fair enough — but an LLM checking its own...
VibeWrenchScan your AI-built app before you ship it
Vibe-coded apps ship with real security holes — leaked secrets, missing headers, open APIs. We scanned 100 and found 318 vulnerabilities. 89 critical.
You built it with prompts — check it the same way. VibeWrench explains each finding in plain language and gives you a fix prompt you can paste straight into Cursor, Claude Code, Lovable, or Bolt. Not "fix your headers" — an actual instruction for your stack.
18 scans, one click. Detects your tech, adjusts checks. Free to try, no card.
VibeWrenchScan your AI-built app before you ship it
Andrei Kniazevleft a comment
Streak and live URLs show who's consistent, but how do you tell quality apart? Tons of projects are technically "live" but held together with duct tape. Does the vibe score look at activity only, or does it factor in stuff like uptime or actual users?
VibeTalentFind vibe coders who actually ship
Andrei Kniazevleft a comment
Had the same thing happen with a web app — wrong security header that nobody caught until it was already in prod. One-line fix, but finding it mid-deploy is a different story. Makes sense to have this running automatically before you even get to that point.
AppovalShip to the App Store with confidence
Andrei Kniazevleft a comment
Finally. Do the agents handle timezone hell properly though? Like Google Calendar + Outlook, people in 3 different timezones — that's always where scheduling stuff breaks down.
Cal.com AgentsAI Agents coming to the best scheduling tool
Andrei Kniazevleft a comment
Ha, I literally have a project sitting in docker compose down on my server for months because I can't bring myself to delete it. Still paying for the disk space. The portfolio embed is what makes this more than just a screenshot tool — it's actually a reason to finally pull the plug. Can it capture multiple pages or just the landing page? Some of my dead projects had cool inner pages that I'd...
Startup ArchiveStop burning money keeping your startup online
Andrei Kniazevleft a comment
Really glad someone built this as open source. I've been stitching together LangGraph + FastAPI for agent-powered endpoints and it's messy. The permission scoping per agent is a nice touch — I learned the hard way that giving an agent full filesystem access "just for testing" is a terrible idea lol. One thing I'd want to know: how does memory persistence work between restarts? Like if I deploy...
OpenMoltLet your code create and manage AI Agents (OpenSource)
Andrei Kniazevleft a comment
The MCP + Claude Code combo is what got me here honestly. I already live in the terminal for most of my dev work and switching to a board app just to move a card always felt like wasted time. Does the CLI let you set priorities or tags when creating tasks? Would be nice to have Claude auto-tag stuff as bug/feature while I'm in the middle of coding.
DocketLike Jira but for indie devs and AI agents