Auditable AI-assisted scientific research: evidence-gated hypothesis routing, isolated computation, independent replication, and anomaly-sensitive representation repair.
Scientific hypothesis-discovery workbench: grounded hypothesis-evidence graphs, synthetic literature with planted causal chains, generate-debate-evolve loops over pluggable offline adapters, Elo tournaments recovering planted skill order, paraphrase dedup, Bayesian evidence accumulation, reproducible reports. NumPy core, CPU-only torch extra.
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
🔬 Harness Vibe Research with Self-evolving AI Scientists
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Automatic and end-to-end scientific research workflow. Produces state-of-the-art level research results.
Modular Multi-Agent System for Scientific Research Assistance
Token-scale scientific discovery engine — autonomous hypothesis generation, experiment execution, and knowledge graph synthesis
Science-Star: A Platform for Building, Extending, and Experimenting with Scientific Agents.