finds.dev← search

// the find

ashishpatel26/500-AI-Agents-Projects

★ 33,511 · Python · MIT · updated Jun 2026

The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation, illustrating how AI agents are transforming sectors such as healthcare, finance, education, retail, and more.

A link collection and starter-code repository for AI agent examples across frameworks like LangGraph, CrewAI, AutoGen, and Agno. It's primarily a curated index of external projects plus 20 self-contained example agents in the `agents/` directory. Aimed at developers who want a quick onramp to agent frameworks or are shopping for a use-case pattern to copy.

The `agents/` directory is the one genuinely useful part — each numbered agent is self-contained with its own `requirements.txt`, `.env.example`, and runnable `agent.py`, so you can actually try something in 5 minutes without untangling a monorepo. The framework comparison table is honest and practical, giving you a real decision matrix rather than cheerleading for a single tool. The link-checker GitHub Action means broken external links get caught before they accumulate. The metadata.yaml convention in each agent folder makes it machine-readable, which matters if you ever want to build tooling on top.

The vast majority of the repo is just a README with links to other people's work — the 500+ claim is marketing for a list of external repos, not 500 implementations here. Only 20 agents actually live in this repo, and they're all basic demos (web research, email drafting, PDF Q&A) that any LangChain tutorial covers. Quality control on the external links is minimal; several point to repos with single commits or no activity since 2023. The React web app in `web/` appears to be an abandoned GitHub Pages viewer that doesn't match the current README structure.

View on GitHub → Homepage ↗

// want more like this?

We dig through GitHub every week and send a few repos picked for what you actually care about — each with an honest take like this one.

Get finds in your inbox → Search again →