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.; emulo: Emulo is an open-source tool that mines your past AI agent coding sessions (e.g., Claude Code, Codex) to build a private working profile. This profile, containing unwritten rules and preferences, allows agents to understand your unique workflow and act more like you before every task.
Reduce LLM token usage and API costs for AI agents.
Tailoring AI agent responses and coding style to user preferences