The 21 runnable agents in the 500-AI-Agents-Projects repo, sorted easy → medium → hard, with the command to run each one

The companion to the reel. PAGE 1 — what the repo really is (21 runnable agents in the agents/ folder, MIT license, 100+ linked projects), how to run any agent in 5 lines, and what happened when we ran the résumé agent (Fit Score 90/100, Recommendation: Hire). PAGE 2 — Level 1, easy: email drafter, news summarizer, résumé parser, social media, recipes, PII sanitizer. PAGES 3–4 — Level 2, medium: web research, code review, PDF Q&A, SQL, issue triage, data analysis, meeting notes, stocks, travel, unit tests, docs, job applications. PAGE 5 — Level 3, hard: customer support (RAG), competitive analysis, multi-agent debate — plus honest notes (free code, paid API calls) and how to turn three agents into a portfolio. Every agent links to its folder with the exact command and the key it needs. Checked on GitHub on September 28, 2026. Independent guide from Hyperautomation Labs — not affiliated with the repo's author or OpenAI.

By submitting, you'll be subscribed to the Hyperautomation AI Report newsletter — three practical AI emails a week. Unsubscribe anytime.

Free. No spam. Unsubscribe anytime.