Loading repository data…
pappukrs / repository
Production-grade AI agent systems built from scratch in JavaScript, covering agent fundamentals, LangGraph workflows, multi-agent collaboration, RAG, vector databases, and AI productization.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
A 40-Day Challenge to Master AI Agent Engineering From first principles to scalable, monetizable AI products.
Agent-30 is an intensive, structured roadmap designed to transform developers into Advanced AI Engineers. Unlike simple tutorials that show you how to call an API, this project focuses on the engineering, architecture, and productization of autonomous systems.
Over the course of 40 days, this repository will evolve from simple scripts into a multi-tenant, knowledge-aware, production-grade AI platform.
"Build the Brain"
We start by building AI agents from first principles—no heavy frameworks, just raw logic and understanding.
"Orchestrate the Team"
Transitioning to LangGraph to build reliable, state-driven multi-agent workflows.
"Unlock the Knowledge"
Giving agents access to deep knowledge through RAG (Retrieval-Augmented Generation) and Vector Databases.
Selected from shared topics, language and repository description—not editorial ratings.
a7ul /
TypeScript agent framework for building production-grade, type-safe AI applications the pydantic ai way
57/100 healthdavid-spies /
Ai-Agent Builder is a production-grade, "backend-less" single-file web application for authoring, configuring, and packaging AI agents. It runs entirely in the browser — no server, no API keys stored, no telemetry — making it invisible to trackers and safe for enterprise environments.
56/100 health"Ship the Business"
Turning the code into a viable SaaS Product.
This project is built on a modern, scalable stack:
By the end of this challenge, the goal is not just to have "code that runs," but to possess the mental models and engineering discipline required to build the next generation of AI startups and enterprise tools.
"The difference between a script and a product is reliability, scalability, and usability."
Agent-30/
├── Phase 1 — Core Agent Engineering/ # Days 1-10
├── Phase 2 — Multi-Agent Systems/ # Days 11-20
├── Phase 3 — Advanced AI & RAG/ # Days 21-30
├── Phase 4 — Productization/ # Days 31-40
├── LICENSE
└── README.md
Created by [Your Name/Handle]
ShayaanPatel /
A production-grade conversational AI flight search agent engineered with n8n, LangChain, and Google Gemini. Orchestrates live SerpAPI lookups, features stateful context window memory, and utilizes custom JavaScript for runtime data normalization.
51/100 healthpraneethb7 /
A production-grade CLI agent built with TypeScript that turns natural language prompts into working HTML, CSS, and JavaScript files. Powered by Groq's LLaMA 3.3 70B model, it runs an autonomous agent loop, planning, generating, and writing code files to your output directory with minimal input from you.
49/100 healthshahbaz957 /
Hands-on practice and production-grade experiments in Generative AI using JavaScript & TypeScript. This repository documents my journey of building AI agents, LLM-powered workflows, and backend-integrated GenAI systems using modern JS/TS stacks.
42/100 healthsrinivas-rc0408 /
"A production-grade 2D Flappy Bird engine featuring an autonomous PID-controlled AI agent, custom particle physics, and a modular state-machine architecture built in vanilla JavaScript. Includes dynamic difficulty scaling, performance-optimized render loops, and an unlockable character system."
49/100 health