
EdgeX11 — Build Your Digital Engineering Workforce
AI engineering workforce that plans, builds, tests, and ships code with human oversight.
@edgex11lz · X
The full gallery
Tech stack
61 projects

AI engineering workforce that plans, builds, tests, and ships code with human oversight.
@edgex11lz · X

Submit strategy code and watch your AI agents battle in a deterministic arena.
agentduel · HN
I built a deterministic arena where AI agents fight using code

Compare AI coding models on real tasks with live previews, cost tracking, and ELO rankings.
@intheworldofai · X
On the World of AI Bench (vibe-coding composite): Claude Fable 5 → 85.2 GPT-5.6-sol → 82.4 kimi-k3 → 81.5 Moonshot’s K3 just walked in and claimed bronze on one of the toughest coding-focused leaderboards out there.

Maps your codebase and cloud infrastructure into architecture diagrams with AI analysis.
@prabhjeet1693 · X
The real challenge with vibe coding isn’t generating code—it’s staying able to understand the system as it evolves. Making architecture, dependencies, and workflows visible can help fight code slop. That’s what we’re exploring with JigsawML. Free demo:

Generate full-stack React apps by describing your idea in Arabic or English.
@codeskyai · X
Meet CodeSky ☁️ the Arabic-first vibe coding platform. Describe what you want — in Arabic or English — pick an AI model, and get a real running app. Clean code, first-class RTL. Start free → #VibeCoding

Track AI coding costs attributed to pull requests, teams, and organizations.
haseebejaz · HN
TokenSpend, the AI ROI Solution

Manage and control your coding agents from any browser or mobile device.
@vilmire_tmp · X
Tired of alt-tabbing between terminals to check if my coding agents were done, stuck, or waiting on approval. So I built ADHDev: control Claude Code / Codex / Cursor CLI from your browser or phone, on every machine you own. AGPL self-hosted edition too.

Task board for AI agents in VS Code with persistent context across chat sessions.
gb2d_hn · HN
It was with the transience of valuable agent session dialogue in mind that I built https://www.agentkanban.io - A key feature is context capture in the tasks which you create on the board and then progress in agent sessions. Supported agents are currently Claude and Github CoPilot in VS Code. All of your context is captured in the task and can be reloaded into new agent sessions at any point in the future. Tool use is intentionally discarded because it is proprietary in nature and therefore brea

Route AI coding tasks to the cheapest capable model based on estimated complexity.
@viiforwinn · X
Hey, let's connect! 🚀 I got tired of the manual grind (picking Claude models, checking diffs for secret leaks, and guessing agent parallel counts), so I automated all three. Built kodemux—it's completely free and open source:

AI assistant that learns your workflow and routes coding tasks across 30+ frontier models.
@otakuaakash · X

Design mobile app interfaces with AI and export to HTML, design tokens, and implementation code.
@9to5_Dad · X
Ai mobile app ui designer with taste

AI coding assistant offering multi-model chat, code generation, refactoring, and agent orchestration.
shreyans_assistiv · Product Hunt
AskCodi Orchestrate agents at scale while reducing cost