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.; codex-mcp-tool: This MCP server integrates Claude/Cursor with the Codex CLI, enhancing AI-powered code interactions. It enables advanced features like file analysis, multi-turn conversations, sandboxed code execution, and structured change management.
Function calling in LLMs
Code Understanding: Explain the architecture of project source code.