Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

Provides ServiceNow ITSM tools (incidents, knowledge, CMDB, user lookups) to AI agents, with an evaluation harness that measures tool-selection accuracy, task completion, and latency.

Clinician-reviewed library on ADHD in children — evaluation, treatment, school, parenting.