headroom: Headroom compresses everything your AI agent reads — tool outputs, logs, RAG chunks, files, and conversation history — before it reaches the LLM. It achieves the same answers with a fraction of the tokens.; PyScrappy: PyScrappy is an AI-native web scraping toolkit designed to transform websites into structured, LLM-ready data. It can be used as a standalone Python library or exposed as an MCP server, enabling AI agents to directly access and process web information.
Reduce LLM token usage and API costs for AI agents.
Empowering AI agents (e.g., Claude, Ollama) to fetch and integrate real-time web data.