13 projects
rotalabs-context
Context intelligence for AI agents - Ingest, search, and subscribe to shared context across your AI systems
rotalabs
Trust Intelligence Research - Core package from Rotalabs
rotalabs-eval
Comprehensive LLM evaluation framework with statistical rigor
rotalabs-probe
Sandbagging detection via activation probes - Detects when AI systems deliberately underperform
rotalabs-steer
Control agent behaviors through activation steering - Apply steering vectors to LLMs at inference time without retraining
rotalabs-verity
Verity: Neuro-symbolic synthesis of verified code using Z3 and LLMs with CE2P feedback
rotalabs-redqueen
Evolutionary adversarial testing framework - Quality-diversity evolution for AI safety research
rotalabs-graph
GNN-based trust propagation for AI systems
rotalabs-fieldmem
Field-Theoretic Memory System - PDE-based memory for AI agents with natural diffusion and thermodynamic forgetting
rotalabs-comply
AI compliance and audit logging infrastructure with multi-framework support
rotalabs-cascade
Configuration-driven orchestration engine for multi-stage decision routing
rotalabs-audit
Reasoning chain capture and decision transparency for AI systems
rotalabs-accel
High-performance inference acceleration with Triton kernels, quantization, and speculative decoding
