Resac AI Agent

Research and action agent that is 2x faster than OpenAI's ChatGPT Agent.

resac-demo.mp4

Clone the Repository

git clone https://github.com/hireshBrem/resac-ai-agent .

Setup

1. Run Apps

Run frontend and agent server.

# client 
cd client
npm install
npm run dev

# agent server
cd agent-server
brew install cairo pkg-config # required for pdf generation
uv run langgraph dev

Client will be available at http://localhost:3000 in your browser.

Agent Server will be available at http://127.0.0.1:2024 and see server logs for langsmith studio (must open link in chrome).

2. Configure Environment Variables

Create a .env.local file:

# env var for the client
cd client
cp .env.example .env

# env var for the agent-server
cd agent-server
cp .env.example .env

3. Use Resac

Open http://localhost:3000 in your browser.

Example prompt you can use to test out Resac:

• "Pull the latest available data from the UNESCO Institute for Statistics on national student-teacher ratios and total teaching staff counts for primary and secondary education. Create a spreadsheet with two tabs: one for primary education and one for secondary. Each should include country name, student-teacher ratio, total number of teachers, gross enrollment, and year of reporting. Add a summary tab highlighting the countries with the most strained and most favorable ratios, sorted accordingly. Ensure consistent country naming across tabs."

Tech Stack

• Python LangGraph agent runtime
• Next.js 16 + React 19 + TypeScript front-end with Claude + LangGraph SDKs
• Document generation helpers through exceljs, pdf-lib, and pptxgenjs for Excel/PDF/PPTX creation.

Contact

⭐️ Star the repo if you found this repo useful! Also don't hesitate to reach out on X(Twitter) ❤️