houtini-lm: Houtini LM connects Claude Code to a local LLM server or any OpenAI-compatible API, offloading bounded tasks to reduce token costs. It provides tools, performance tracking, and model routing for efficient delegation. Claude remains the orchestrator for complex reasoning, while cheap local models handle grunt work.; xLAM: xLAM is a research repository for Large Action Models (LAMs), which aggregates and unifies agent trajectories from diverse environments into a consistent format. It streamlines the creation of a generic data loader optimized for agent training, enabling robust model development across various scenarios.
Generate test stubs
Function calling in LLMs