Aslan

This project was inspired by a course from @DeepLearningAI. I would like to thank them too!

GitHub - aslansd/nvidia-nat-langgraph-deep-research-agent: A Deep Research Agent Using NVIDIA NeMo Agent Toolkit and Deep Agent Framework of Langgraph A Deep Research Agent Using NVIDIA NeMo Agent Toolkit and Deep Agent Framework of Langgraph - aslansd/nvidia-nat-langgraph-deep-research-agent

📦 Check it out: github.com/aslansd/nvid... 👉 Built on top of NVIDIA NeMo’s framework-agnostic agent runtime and LangGraph’s workflow engine for stateful agent execution.
Would love your feedback and contributions! 🙌

combining stateful planning, iterative exploration, and result synthesis in a seamless pipeline. It’s designed for extensible, production-ready AI research automation with modern agent tooling.

🚀 Just open-sourced a Deep Research Agent built using NVIDIA NeMo Agent Toolkit (NAT) + LangGraph Deep Agent Framework!
This project demonstrates how to orchestrate multi-agent workflows for complex research tasks —

Built upon the original ADK sample: [https://github.com/google/adk-samples/tree/main/python/agents/machine-learning-engineering]. Full Colab notebook & Gradio UI included. Check it out: [https://github.com/aslansd/MLE-Agent-GoogleADK-Gradio] #MLE #MultiAgent #GenAI

Just released my MLE-STAR inspired Machine Learning Engineering Agent! 🤖 It uses the Google ADK to orchestrate Initialization, Refinement, and Ensemble agents. Trains SOTA models, driven by search and targeted code refinement.

Finally, this app was inspired by two courses from @DeepLearningAI and @LangChainAI Academy. I would like to thank them!

GitHub - aslansd/deepagent_researcher_analyse_visualise: Build a deep agent researcher which analyses and visualises the information Build a deep agent researcher which analyses and visualises the information - aslansd/deepagent_researcher_analyse_visualise

Check it out here 👇
GitHub (code): github.com/aslansd/deep...
Streamlit app (try it out): d3yjnms2ch6yxcthmrvqnn.streamlit.app
Would love feedback from researchers, builders, and anyone interested in multi-agent systems 🚀

The results?
📊 Final answers with explanations
📈 Automatically generated charts
📝 Full trace of every step the system took
It’s like having a research assistant that works systematically and shows its work!

My app combines all of this into a multi-agent framework:
A Planner breaks down your research question
Specialized agents (web researcher, chart generator, summarizer) handle subtasks
Everything is orchestrated into a transparent workflow you can trace

Traditional LLM agents can be “shallow” — they just loop through tools and struggle with long, complex tasks.
Deep Agents (a new feature in LangGraph) bring:
✅ Task planning (TODOs)
✅ Sub-agent delegation
✅ Context offloading to files
✅ Robust reasoning prompts

It’s a Streamlit app powered by LangGraph Deep Agents that can take your research question, plan a workflow, fetch data, generate charts, and explain results step by step.

GitHub - aslansd/deepagent_researcher_analyse_visualise: Build a deep agent researcher which analyses and visualises the information Build a deep agent researcher which analyses and visualises the information - aslansd/deepagent_researcher_analyse_visualise

🚀 Excited to share something I’ve been building: the Multi-Agent Deep Research Assistant 🧠✨

🔗 GitHub: github.com/aslansd/deep...
🔗 App: d3yjnms2ch6yxcthmrvqnn.streamlit.app

Big thanks to @DeepLearningAI & @LangChainAI Academy for the resources that made this possible.

GitHub - aslansd/multi-modal-rag-web: A Multi-Modal RAG Application Built with Streamlit Using a Lightweight Ollama Model A Multi-Modal RAG Application Built with Streamlit Using a Lightweight Ollama Model - aslansd/multi-modal-rag-web

Multi-Modal RAG App (Streamlit + Ollama)
Built a lightweight Retrieval-Augmented Generation (RAG) system that processes both text + image docs. Users can load files, build a vector store, and run retrieval-grounded QA.
github.com/aslansd/mult...

GitHub - aslansd/open_deep_reasearch_mobile: A React Native plus Expo Go App for open_deep_research Framework of LangChain/LangGraph A React Native plus Expo Go App for open_deep_research Framework of LangChain/LangGraph - aslansd/open_deep_reasearch_mobile

React Native + Expo Go App for Open Deep Research
Brought the same framework to mobile, enabling research automation on the go.
github.com/aslansd/open... expo.dev/accounts/asa...

GitHub - aslansd/open_deep_research_web: A Streamlit App for open_deep_research Framework of LangChain/LangGraph A Streamlit App for open_deep_research Framework of LangChain/LangGraph - aslansd/open_deep_research_web

Streamlit App for Open Deep Research
Adapted LangChain’s Open Deep Research (LangGraph) into a Streamlit app to support advanced research workflows: ingestion, retrieval, multi-modal analysis, and context-aware Q&A.
github.com/aslansd/open...
rneaovknvzddyykhkeu2et.streamlit.app

Over the past two weeks at LangTechAI, I built 3 generative AI apps on top of LangChain / LangGraph frameworks — inspired by courses from @DeepLearningAI & @LangChainAI Academy.

Feel free to use any one of the above apps and I would be happy to receive any feedback.

These three projects were not possible without taking the online courses offered by DeepLearningAI and LangChain Academy. Here, I would like to thank them. I would like to thank CrewAI, Gradio, Ollama, and TogetherAI too.

cycles. It will provide the user a final markdown summary with all sources used.

(via seven different search APIs: DuckDuckGo, Tavily, Perplexity, Linkup, Exa, ArXiv, and PubMed), summarise the results of web search, reflect on the summary to examine knowledge gaps, generate a new search query to address the gaps, search, and improve the summary for a user-defined number of

In the third project, I extended one of the LangChain apps called Ollama Deep Researcher which is a local web research assistant built upon the multi-agent framework of LangGraph that uses any LLM hosted by Ollama. It accepts a topic and it will generate a web search query, gather web search results

In the second project, I built a Dungeon game simulating a fantasy world composed of kingdoms, towns, characters, and inventories powered by one of the LLMs provided by TogetherAI and used Gradio as a user interface. Again all the codes and results are brought in one notebook.

given by the user for their startup considering their expertise.For this purpose, I used the multi-agent framework of CrewAI combining it with LangChain, Gradio, and one of the open source LLMs of Ollama. All the codes and results are provided in a notebook.

In the first project, I simulated an environment similar to a startup having three cofounders: the first cofounder is more technical, the second cofounder is more product oriented, and the third cofounder is more business one. These three cofounders do brainstorming about various topics

GitHub - aslansd/startup-brainstorming: A multi-agent system app to simulate brainstorming part of a startup. A multi-agent system app to simulate brainstorming part of a startup. - aslansd/startup-brainstorming

Here are the three projects that I have done during past few months under LangTechAI:

github.com/aslansd/star...
github.com/aslansd/dung...
github.com/aslansd/olla...

Extra Day 26

Extra Day 25

Extra Day 24