AI-Powered Neuroscience

Talk to Your Brain

Natural language EEG lab notebook. Train pattern classifiers, analyze connectivity, compare sessions — all by talking to an AI copilot that reads your live brain signals.

See It In Action

Watch realistic conversations with your brain copilot

Brain State Monitoring

Ask about your current mental state

how's my signal?

All channels read 'good', quality 0.98 — trustworthy signal.

Pattern Training

Train custom mental state classifiers

train a pattern called 'meditation'

Starting pattern training for 'meditation'. I'll guide you through recording segments. First, I need a baseline. Sit normally with eyes open. Ready to record 'rest' for 4 seconds? (say yes when ready)

Spectral Analysis

Deep frequency-domain analysis

analyze my alpha rhythm

Spectral analysis: • Individual alpha peak (IAF): 10.2 Hz • Alpha power: 0.73 (dominant) • 1/f slope: -1.1 (typical healthy EEG) • Spectral entropy: 0.68 (moderate complexity) • Frontal alpha asymmetry: -0.05 (balanced)

Connectivity Analysis

Network topology and synchrony

show connectivity in the alpha band

Alpha-band connectivity (amplitude coupling): Mean correlation: 0.34 Strongest pair: C3↔C4 (r=0.72) — motor cortex synchrony Most connected: C3 (6 strong links) Least connected: Fp1 (2 weak links)

Comprehensive Analysis Tools

All the capabilities of a neuroscience lab, accessible through conversation

Real-Time Brain State

Monitor focus, relaxation, engagement with session-relative indices

Pattern Recognition

Train custom classifiers with L2 + group-lasso, LORO-CV validation

Spectral Analysis

IAF detection, 1/f slope, theta/beta ratio, spectral entropy

Connectivity

Cross-channel amplitude coupling in any frequency band

Session Recording

Capture labeled windows, compare with effect sizes (Cohen's d)

Artifact Detection

Eye blinks (single/double), jaw clenches, motion artifacts

Jupyter Notebooks

Auto-generate analysis notebooks

Quick Start

One command. No Node.js required.

Install
curl -sSL https://raw.githubusercontent.com/pieeg-club/PiEEG-agent/main/install.sh | bash
Launch Web Interface
pieeg-agent web

Open http://localhost:8000 for chat, live brain state cards, pattern training UI

Test with Synthetic Data (No Hardware)
Terminal 1:pieeg-server --mock --lsl
Terminal 2:pieeg-agent web

What the installer does:

  • Creates Python virtual environment
  • Installs all dependencies
  • Sets up command-line launcher
  • Runs verification tests

Built for Research

Designed for neurofeedback research and UX prototyping — not clinical use

Ingestion Never Blocks

Dedicated LSL thread, ring buffer — no sample loss even if LLM is slow

LLM Pulls, Never Pushed

Tools request state on demand — token costs stay sane

Language-Sized Representations

Events, not voltage arrays — models reason about "focus_high", not floats

Decoupled Layers

Swap providers, run without LLM, test with mock — debuggable, testable, maintainable

Safe by Default

Dry-run, cooldown, audit log — AI can't spam device commands

Provider Agnostic

Anthropic, OpenAI, Groq, Ollama, LM Studio — your choice, your hardware

Ready to Talk to Your Brain?

Join researchers and makers building the future of brain-computer interfaces

Open source • CC BY-NC 4.0 License • Non-commercial use