This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend
I built Fathom Rebuild, an AI meeting copilot for a friend who spends a lot of time in meetings and often needs to go back through transcripts to find specific decisions, action items, or things someone mentioned.
Instead of manually searching through long meeting transcripts, the app lets you ask questions across your meetings and get answers with references back to the relevant transcript.
It has two main workflows:
The goal was simple: make meeting history something you can actually talk to instead of something you have to search through.
🎥 Walkthrough:
🚀 Deployed App:
The project is completely open source:
🔗 GitHub:
A Fathom-style meeting assistant built for a 24-hour assignment: record → transcript → AI summary, decisions, action items and highlights, plus search and "ask across all meetings" with cited answers.
Stack: Next.js 15 (App Router) · TypeScript · Tailwind CSS + shadcn/ui · LangChain + LangGraph · Groq · optional Supabase/Postgres.
The real meeting-capture layer (Zoom/Meet/Teams bot) is intentionally stubbed. See Capture layer.
Prerequisites: Node 20.9+ (Node 22 recommended) and a free Groq API key.
git clone https://github.com/Adii0906/fathom-rebuild && cd fathom-rebuild
git checkout claude/happy-hopper-jytoyu # until this is merged to main
npm install
cp .env.example .env.local # then edit it
npm run dev # http://localhost:3000
The app is fully populated on first load, because the seed data needs no API key or database. GROQ_API_KEY is only used when you:
The repository contains the application code as well as the agent development logs.
I built the application around an agentic workflow using LangGraph and LangChain, with Groq for LLM inference.
The architecture is split into separate workflows for different tasks instead of putting everything into one large prompt.
The main flow looks roughly like:
Transcript → Processing → Analysis → Structured Information
and for cross-meeting questions:
Question → Retrieval → Relevant Meeting Context → Agent Reasoning → Cited Answer
I also added references to the source transcript so the user can trace an answer back to where the information came from.
The goal was to use the AI agent for actual reasoning and workflow orchestration rather than simply sending a transcript to an LLM and asking it to summarize.
Open innovation made it possible for me to build the entire agent workflow around tools and frameworks that I could inspect, modify, and experiment with.
Using open-source frameworks like LangGraph and LangChain meant I could control how the different AI steps were connected instead of treating the intelligence as a black box.
It also makes the project easier for someone else to extend — whether that's adding new meeting analysis nodes, changing the retrieval strategy, adding another model provider, or building completely new workflows on top of the existing system.