---
title: Deep Research Agents
emoji: 🔬
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false
license: mit
app_port: 8501
---

# Deep Research Agents

Multi-agent deep-research pipeline — **Researcher → Critic → Synthesizer → Writer** — with FAISS memory across sessions.

**Stack:** Groq + LangGraph + FAISS + Streamlit

## Files

| File | Purpose |
|------|---------|
| `app.py` | Everything — UI, agents, memory, graph |
| `requirements.txt` | Python dependencies |
| `Dockerfile` | Hugging Face Spaces deploy |
| `README.md` | This file |

## Local run

```bash
pip install -r requirements.txt
set GROQ_API_KEY=your_key_here
streamlit run app.py
```

## Hugging Face deploy

1. Create a **Docker** Space on [huggingface.co/new-space](https://huggingface.co/new-space)
2. Upload these 4 files
3. Add `GROQ_API_KEY` as a **Repository Secret** in Space settings

## Environment variables

| Variable | Required | Default |
|----------|----------|---------|
| `GROQ_API_KEY` | Yes | — |
| `GROQ_MODEL` | No | `llama-3.3-70b-versatile` |