Enables autonomous agents and multi-agent frameworks to discover and execute modular, class-based tools over SSE with a standardized response contract.
Exposes local LM Studio language models as MCP tools, enabling chat completions and model listing through a local OpenAI-compatible API without requiring API keys.
Exposes local Ollama instances as tools for Claude Code, allowing users to offload code generation, text drafting, and embedding tasks to local GPUs. It supports multi-turn conversations and model management through the Model Context Protocol.
Enables agents to discover, evaluate, and serve task-specialist models (embeddings, reranking, classification, extraction) with OpenAI-compatible endpoints and MCP tools for routing, embedding, reranking, and extraction.
Exposes the KappaML API as tools for AI assistants, enabling user management, model operations, predictions, learning, forecasting, metrics, and checkpoint management.