A task-aware context compression layer for Agent workflows, RAG pipelines, and AI Coding assistants, reducing noisy logs, retrieval chunks, and code context into high-signal LLM inputs via CLI, Python SDK, and MCP.
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.
Enables converting web pages to clean Markdown via MCP, compressing token usage by roughly 95% in under 150ms to support LLM context windows and RAG pipelines.
A generic Model Context Protocol (MCP) server for high-accuracy document reranking using sentence-transformers (Cross-Encoder). Ideal for enhancing RAG and AI agent decision-making. sentence-transformers (Cross-Encoder) を使用して文書の関連度を再計算・ソートする汎用 MCP (Model Context Protocol) サーバー。
A local RAG context optimizer MCP server that filters retrieved context to the minimum an LLM needs to answer correctly, using a cross-encoder and optional calibration.
