All member projects

Code · Built by members

AutoBlog AI

A LangGraph agent that researches a topic and writes a full SEO-ready blog post end to end.

Conceptual illustration: A LangGraph agent that researches a topic and writes a full SEO-ready blog post end to end.
AI-generated editorial illustration, not a product screenshot.

What it is

AutoBlog AI is an agent system that takes a topic, researches it in real time and writes a complete, search-friendly blog post on its own. It was built to see how far an agent workflow can go in automating content writing from start to finish.

The work showed that a reliable multi-step agent depends more on graph design, state handling and failure handling than on the model itself. It is still a work in progress.

What it does

  • Takes a topic and researches it in real time
  • Writes a full blog post shaped for search
  • Strict structured output between graph steps
  • FastAPI backend with custom error handling and logging
  • CI/CD with GitHub Actions

Built with

  • Python
  • LangGraph
  • LangChain
  • Groq
  • Tavily
  • FastAPI
  • Streamlit
  • GitHub Actions
  • agents

More from the community

Demo

One neuron at a time

by Caleb

Push single neurons in small open models and turn them into villains, flatterers or pirates. Try the recorded replies, then run it yourself.

Code

governed-agent

by Jeremy

Capability-based security, scope-bounded planning and out-of-band audit for autonomous LLM agents.

Website

Dave, a personal agent

by Chris

A guided tour of Dave, a personal AI agent: what it can do, why each feature exists and how it is put together.

Back to all member projects