
LoopFlow — the tutorial
Describe self-correcting coding workflows in plain English and run them until tests pass.
forgeapp
The full gallery
Tech stack
18 projects

Describe self-correcting coding workflows in plain English and run them until tests pass.
forgeapp

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

Share files and text directly between browsers without server storage or login.
@bytestreak · X
Building a frictionless, forever free file sharing utility tool. Check it out here:

Backend infrastructure that keeps AI agents alive with durable execution and state management.
iacguy · HN
Show HN: Durable AI agents without the workflow engine

Get a live server for your AI agent by describing your goal.
@ServerForAgent · X

Turn HTML, Markdown, notebooks, or PDFs into private, shareable websites instantly.
@thryvate · X
My AI built something cool, let’s share it with some friends.

Secure AI agent actions with code checks, permission gates, and approval workflows.
@RElharrak39428 · X

Browse and install 1,800+ MCP servers ranked by trust score and risk level.
@Shidesheng0218 · X
🔥 Just launched: MCP Market 1,600+ MCP servers ranked by Trust Score, Risk Level, and install success data. For Cursor, Claude, VS Code, and Codex. Copy config. Know it works. No more guessing. #MCP #AITools #Cursor #Codex #BuildInPublic

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

Review GitHub pull requests in a native app without opening github.com.
othmanosx · HN
I still don't like the fact that AI is adding more stuff for us to read, it's accelerating the code production but slowing down the code review. I built my own code reviewer as well ( https://pyor.review/ ), surfacing the important stuff first is the right track, but adding more stuff to read is daunting, but asking AI to just point you to what you need to focus on and skim the noise is what I'm leaning more towards.

Browse and test OpenAPI endpoints, compare specs, and generate mock data in your browser.
@_codewithshahid · X

Extract code, design tokens, fonts, colors, and media from any website instantly.
@bharatmodi2014 · X
Extract code, design tokens, fonts, colors, and media instantly. Save everything to the cloud, organize your library, and regenerate designs with your favorite AI.