AgentBoard: A Discovery Platform for the Agentic AI Community

Source: Dev.to

Introduction

This is a submission for the DEV Weekend Challenge: Community. I write for The Agentic Engineer, a weekly newsletter tracking the agentic AI space. The readers are builders who ship autonomous agents, multi‑agent workflows, and AI tools for a living.

The number‑one question I get is: “Which framework should I use?”
There are 15+ major agent frameworks right now, with new ones launching weekly. You either scroll GitHub trending, ask Twitter, or hope someone wrote a comparison post this month. There’s no single place to browse, compare, and discover what’s out there.

AgentBoard fills that gap: a front‑door for agentic AI builders to discover the tools they’re building with.

What is AgentBoard?

AgentBoard is an open directory for AI agents, frameworks, and tools—think Product Hunt meets Awesome Lists, but specifically for the agentic AI community.

• Live site: https://natearcher-ai.github.io/agentboard
• No login, no backend. Everything runs client‑side with localStorage.

Features

• Browse & search a curated directory of AI agents.
• Filter by category (dev tools, automation, research, infrastructure, etc.).
• Sort by GitHub stars, upvotes, or newest.
• Detailed agent profiles with tech stack, creator, description, and links.
• Upvote and bookmark favorites (persist locally).
• Submit your own agent through a simple form.
• Community stats dashboard on the home page.
• Beautiful dark theme with smooth animations.
• Fully responsive (mobile + desktop).

Screenshots

Home

The landing page features a hero section, community stats, and featured agents.

Discover

Filterable, searchable directory with category tabs and sort options.

Submit

Clean form to contribute your own AI agent to the directory.

(Screenshots omitted for brevity.)

Stack

• Framework: React 19
• Build tool: Vite
• Styling: Tailwind CSS v4
• Routing: React Router
• Icons: Lucide

The project is a static single‑page application. The seed data lives in a single JavaScript file; adding a new agent is just adding an object to an array. The UI uses a dark theme with a purple/blue gradient palette, hover animations on cards, and real‑time search on the Discover page.

Deployment

• Deployed via GitHub Actions to GitHub Pages.
• Pushing to main updates the site in under a minute.

License

MIT licensed. Pull requests are welcome.

View on GitHub: https://github.com/natearcher-ai/agentboard