AI Agent Skills

Dataset and benchmark for RAG on company internal documents.

A tool for evaluating LLMs

[ICML 2026] RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings

Production-grade RAG API built in Rust. Hybrid search with HNSW dense vectors and BM25 sparse matching, cross-encoder reranking, layout-aware document extraction via Doc…