awesome-ai-apps

I’ve been collecting different open-source examples of agents that use these patterns (RAG, workflows, multi-agent setups, etc.) here:https://github.com/Arindam200/awesome-ai-apps Feel Free to try it and let me know!

I read a good post from Anthropic about how people build effective AI agents. The biggest thing I took away: keep it simple. The best setups don’t use huge frameworks or fancy tools. They break tasks into small steps, test them well, and only add more stuff when needed. A few things I’m trying to follow: 1. Don’t make it too complex. A single LLM with some tools works for most cases. 2. Use workflows like prompt chaining or routing only if they really help. 3. Know what the code is doing under the hood. 4. Spend time designing good tools for the agent. I’m testing these ideas by building small agent projects. Would love to hear how you all build agents! Link to Anthropic's Post: https://www.anthropic.com/engineering/building-effective-agents If you’re curious, I’m sharing the agents here: https://github.com/Arindam200/awesome-ai-apps

Recently, I was exploring RAG systems and wanted to build some practical utility, something people could actually use. So I built a Resume Optimizer that helps you improve your resume for any specific job in seconds. The flow is simple: → Upload your resume (PDF) → Enter the job title and description → Choose what kind of improvements you want → Get a final, detailed report with suggestions Here’s what I used to build it: LlamaIndex for RAG Nebius AI Studio for LLMs Streamlit for a clean and simple UI The project is still basic by design, but it's a solid starting point if you're thinking about building your own job-focused AI tools. If you want to see how it works, here’s a full walkthrough: https://www.youtube.com/watch?v=J8qIR29zCHU And here’s the code if you want to try it out or extend it: https://github.com/Arindam200/awesome-ai-app

Hey folks, I've been working on Awesome AI Apps, where I'm exploring and building practical examples for anyone working with LLMs and agentic workflows. It started as a way to document the stuff I was experimenting with, basic agents, RAG pipelines, MCPs, a few multi-agent workflows, but it’s kind of grown into a larger collection. Right now, it includes 25+ examples across different stacks: - Starter agent templates - Complex agentic workflows - MCP-powered agents - RAG examples - Multiple Agentic frameworks (like Langchain, OpenAI Agents SDK, Agno, CrewAI, and more...) You can find them here: https://github.com/arindam200/awesome-ai-apps I'm also playing with tools like FireCrawl, Exa, and testing new coordination patterns with multiple agents. Honestly, just trying to turn these “simple ideas” into examples that people can plug into re

Recently, I was exploring the idea of using AI agents for real-time research and content generation. To put that into practice, I thought why not try solving a problem I run into often? Creating high-quality, up-to-date newsletters without spending hours manually researching. So I built a simple AI-powered Newsletter Agent that automatically researches a topic and generates a well-structured newsletter using the latest info from the web. Here's what I used: - Firecrawl Search API for real-time web scraping and content discovery - Nebius AI models for fast + cheap inference - Agno as the Agent Framework - Streamlit for the UI (It's easier for me) The project isn’t overly complex, I’ve kept it lightweight and modular, but it’s a great way to explore how agents can automate research + content workflows. If you're curious, I put together a wa

Recently, I was exploring the OpenAI Agents SDK and building MCP agents and agentic Workflows. To implement my learnings, I thought, why not solve a real, common problem? So I built this multi-agent job search workflow that takes a LinkedIn profile as input and finds personalized job opportunities based on your experience, skills, and interests. I used: - OpenAI Agents SDK to orchestrate the multi-agent workflow - Bright Data MCP server for scraping LinkedIn profiles & YC jobs. - Nebius AI models for fast + cheap inference - Streamlit for UI (The project isn't that complex - I kept it simple, but it's 100% worth it to understand how multi-agent workflows work with MCP servers) Here's what it does: - Analyzes your LinkedIn profile (experience, skills, career trajectory) - Scrapes YC job board for current openings - Matches jobs based on yo

Hey Folks, I've been playing around with the new Qwen3 models recently (from Alibaba). They’ve been leading a bunch of benchmarks recently, especially in coding, math, reasoning tasks and I wanted to see how they work in a Retrieval-Augmented Generation (RAG) setup. So I decided to build a basic RAG chatbot on top of Qwen3 using LlamaIndex. Here’s the setup: Model: Qwen3-235B-A22B (the flagship model via Nebius Ai Studio) RAG Framework: LlamaIndex Docs: Load → transform → create a VectorStoreIndex using LlamaIndex Storage: Works with any vector store (I used the default for quick prototyping) UI: Streamlit (It's the easiest way to add UI for me) One small challenge I ran into was handling the <think> </think> tags that Qwen models sometimes generate when reasoning internally. Instead of just dropping or filtering them, I thought it might