Massachusetts Institute of Technology

PoggioAI

Proof-Oriented Generative General Intelligence Orchestration: Agentic Investigation

Try PoggioAI/MSc, a multi-agent AI system that turns research hypotheses into high-quality, literature-grounded, experiment-backed papers with minimal human steering.

Get Started View on GitHub Join us on Discord Read the Papers

About the Project

PoggioAI

Current AI systems require on the order of 10² to 10³ prompts to go from a research idea to a written paper. PoggioAI aims to reduce this to up to 10 human interactions.

This is not about fully automating research or replacing human creativity. PoggioAI focuses on the rigorous establishment of ideas: matching theory with experiments, distinguishing correlation from causation, proposing parallel explanations and testing them. The human provides the idea; the system does the structured work of turning it into a solid manuscript.

GitHub Repository

Getting Started

5-Minute Quickstart to MSc

Cost: ~$2–10Time: 15–40 minRequires: one API key

# 1. Bootstrap environment (one-time, ~5 min)
./scripts/bootstrap.sh researchlab minimal

conda activate researchlab

# 2. Set your API key (only one provider needed)
cp .env.example .env
echo "ANTHROPIC_API_KEY=your_key_here" >> .env

# 3. Validate setup without spending tokens
python launch_multiagent.py --task "test" --dry-run

# 4. Run the included quickstart example (~$3)
python launch_multiagent.py \
  --task "$(cat examples/quickstart/task.txt)" \
  --output-format markdown \
  --no-counsel \
  --no-log-to-files

After the run, look in results/MSc_Student_<timestamp>/ for your generated paper and artifacts.

Full documentation on GitHub

How It Works

From Hypothesis to Paper

PoggioAI orchestrates 22 specialist agents through a structured research pipeline. Each stage produces artifacts that feed into the next, with human checkpoints for steering.