Define a team of AI researchers. Ask a question. Get tested, documented, peer-reviewed findings. Powered by any LLM.
Agents hypothesise, write code, run experiments in a sandbox, peer review results, and refine — automatically.
OpenAI, Anthropic, Google Gemini, Groq, Ollama, or any OpenAI-compatible endpoint. Bring your own keys.
Define teams via YAML or auto-generate them from a domain description. Each agent has unique expertise.
Professional reports with full phase breakdowns, agent contributions, code, experiment results, and peer reviews.
API keys stay local. Nothing leaves your machine except API calls to your chosen LLM provider.
Watch your research team work in real-time. Live event feed, phase progress, experiment results as they happen.
Start immediately with pre-built teams, or create your own in minutes
Threat analysis, cryptography, defence
Quantum, neuro, maths, physics, cosmology
Genomics, molecular modelling, pharma
Technical, fundamental, risk, sentiment
Network mapping, signals, cloud sec
Strategy, market analysis, legal, finance
Error correction, algorithms, simulation
Auto-generate from any domain description
Self-host free forever, or let us handle the infrastructure