VentureForge / README.md
Raiquia's picture
fix readme
8a296e8
|
Raw
History Blame Contribute Delete
2.22 kB
---
title: VentureForge - AI Startup Discovery
emoji: πŸš€
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 6.14.0
app_file: app.py
python_version: '3.13'
pinned: false
tags:
- amd-hackathon-2026
- ai-agents
- startup-ideas
- multi-agent
- paul-graham
short_description: Autonomous multi-agent system for startup idea discovery
---
# VentureForge πŸš€
An autonomous multi-agent system that discovers startup ideas by mining real user pain points from online communities, evaluating them with Paul Graham-inspired criteria, and generating investor-ready pitch briefs.
**Built for AMD AI Hackathon | Track 1: AI Agents & Agentic Workflows**
## Features
- πŸ” **Pain Point Mining** from Hacker News, Product Hunt, and web search
- πŸ€– **6 Specialized Agents** (Orchestrator, Miner, Generator, Scorer, Writer, Critic)
- βœ… **Binary Rubric Evaluation** (yes/no checks, not subjective scores)
- πŸ”„ **Reflection Loop** with adversarial critique (max 3 revisions)
- πŸ“Š **Real-time Progress** tracking in Gradio UI
- 🎯 **Token Optimized** for vLLM 2048 token limit
## How to Use
1. **Set API Keys** in Space Settings β†’ Repository secrets:
- `YOUTUBE_API_KEY` (required)
- `PRODUCTHUNT_API_KEY` (optional)
` (optional)
1. **Enter a domain** (e.g., "developer tools", "healthcare", "fintech")
2. **Click "Start Discovery"** and watch the agents work!
3. **View results** in the tabs:
- Pain Points (with evidence sources)
- Ideas (generated from pain points)
- Scored Ideas (8 binary checks)
- Pitch Briefs (investor-ready)
- Critiques (adversarial review)
## Architecture
```
Orchestrator β†’ Pain Point Miner β†’ Idea Generator β†’ Scorer β†’ Pitch Writer β†’ Critic
↓
(reflection loop)
```
## Performance
- **Duration:** ~2 minutes per domain
- **Token Optimized:** One-at-a-time generation + compressed prompts
- **Reliable:** 0 JSON failures on all domains (healthcare, developer tools, finance)
## License
MIT License - see [LICENSE](LICENSE) file for details
---
**Built with ❀️ for AMD AI Hackathon**