Enables users to register and manage city entities, discover their MCP tools, and orchestrate calls to those tools while combining results into a single response.
Provides local-first, zero-LLM memory retrieval for AI agents like Claude Code and Codex, enabling verbatim recall of stored notes and context through tools such as fidelis_recall and fidelis_orient.
Transforms AI assistants into a full ML engineering environment for training and fine-tuning models across multiple backends (local GPU, Mistral, Together AI, OpenAI) and cloud providers (Lambda Labs, RunPod, SSH-accessible VPS), with dataset management, experiment tracking, cost estimation, and deployment to Ollama/Open WebUI.
A template repository for building Model Context Protocol (MCP) servers that enables developers to create interactive AI agents with real-time bidirectional communication capabilities through WebSocket and SSE endpoints.