Search Packages

kalibr

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

pybandits

Python library for Multi-Armed Bandits

oat-llm

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

mabalgs

:bust_in_silhouette: Multi-Armed Bandit Algorithms Library (MAB) :cop:

marketing-agent-example

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

autoresearch-prompt-manager

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

onn

Online Deep Learning: Learning Deep Neural Networks on the Fly / Non-linear Contextual Bandit Algorithm (ONN_THS)

autoresearcher-shonku

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

shonku

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

preferred-pictures

A client for the PreferredPictures API

tsroots

TSRoots: A Python package for efficient Gaussian process Thompson sampling in Bayesian optimization via rootfinding.

llm-cost-reduction

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

llm-cost-optimizer

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

fonz-dial

Online weight optimization via Thompson Sampling — learns optimal configurations from outcome feedback.

kusp-dial

Online weight optimization via Thompson Sampling — learns optimal configurations from outcome feedback.