Sovereign models, reasoning research, and an open ecosystem.
Labs is where NeuroCluster builds its own models — not wrappers around someone else's. Supernova reasoning research, public benchmarks, and open tooling come together here, the proof beneath the platform.
This is the door for technical evaluators, infrastructure partners, and the European research community — benchmark-led, anti-hype, and reproducible.
Three ways into Labs
Supernova reasoning research
Post-transformer reasoning, ARC-AGI, theorem proving, and benchmark methodology.
Open sourceOpen ecosystem
Public eval harnesses, experiment logs, governance tooling, and reproducible artifacts.
ModelsModels & Supernova stack
Sovereign models running on the platform — from Supernova reasoning to Geitje language foundations.
Research areas
Benchmark-led research lines designed for efficient, verifiable reasoning on sovereign infrastructure.
Hierarchical Reasoning
Multi-step inference architectures that decompose complex problems into verifiable stages.
Verifiable AI
Reasoning traces, formal verification, and theorem-proving experiments with Lean.
Agentic Systems
Multi-agent coordination with governance boundaries and auditable tool execution.
Memory Systems
Persistent context, retrieval-augmented reasoning, and long-horizon task memory.
AI Governance
Policy-aware research aligned with enterprise deployment and EU regulatory requirements.
Efficient Inference
Sample efficiency, compute budgets, and energy-per-correct-answer metrics.
An active, reproducible ecosystem
12+
Open repositories
4
Benchmark suites
3
Research papers
24+
Contributors
European research & scale-up
Labs is embedded in the European AI ecosystem — EuroHPC compute, university partnerships, and grant-funded research programmes.