llmtrim: llmtrim is a local proxy that intelligently compresses LLM API requests by removing wasted tokens, significantly reducing billing costs without impacting the quality of the LLM's responses. It offers versatile deployment options, including a proxy, CLI, MCP server, or library for various programming languages.; 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.
Reducing LLM API costs for AI agents (e.g., Claude Code, Cursor, Aider).
Function calling in LLMs