Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

Offloading DOCA-based Adaptive Routing onto NVIDIA BlueField-2 DPU. (卸载基于DOCA的自适应路由到NVIDIA BlueField-2 DPU上)

Krako 2.0 – Energy-efficient, triadic multi-tier inference infrastructure enabling adaptive routing across heterogeneous edge–cloud nodes.

Ant Colony Optimization algorithm for the shortest path problem

Learning Automata algorithm for the shortest path problem

Databricks-native adaptive provider-selection pattern for AI execution systems. Delta Lake medallion pipelines, MLflow training, Lakeflow Jobs, Mosaic AI Model Serving.

Qomni Planner v0.59: Adaptive Cognitive Routing with Online Learning Loops for Edge AI Inference — Percy Rojas Masgo, CEO Condesi Perú · Qomni AI Lab

LangChain integration for Kalibr. Route every LangChain LLM call to lower-cost model paths without degrading performance.

Contextual Thompson Sampling router for multi-provider LLM APIs. Zero config.

Particle Swarm Optimization algorithm for the shortest path problem

LLM routing engine that dispatches prompts to the cheapest capable model

KERNEL v4.2 est un scheduler cognitif adaptatif pour LLMs intégrant LATS, Reflexion et Meta-Prompting. Il optimise dynamiquement le routing du raisonnement selon la complexité (1-5) pour maximiser la précision et réduire les hallucinations. Propulsé par la vision Lichen-Collectives.

Policy-driven execution-lane selector — routes TaskProposal to claude_cli, codex_cli, or aider_local with fallback, escalation, and adaptive routing.

CAP6614-Fall2025: Adaptive noise-type routing CNN that classifies and denoises images via specialized branches, compared against a unified model across MNIST, CIFAR, and STL-10. UCF Final Project.

Qomni Engine v8: Adaptive Cognitive OS — Crystal Distillation + CRYS-L v2 (open) + Learning Loop Planner · Percy Rojas Masgo, Qomni AI Lab

Ant Colony Optimization algorithm for the shortest path problem

Enable deterministic distributed execution for AI workflows with replay-safe billing, contention safety, and trust-driven scheduling.