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.; mermaid-code: Mermaid Code is a local-first desktop editor for Mermaid diagrams, built on Mermaid Live Editor and enhanced with Tauri for native features. It integrates AI agents like Claude Code and Codex, allowing them to create, modify, and explain diagrams directly within the app, leveraging local file access and an MCP server for AI-native workflows.
Reduce LLM token usage and API costs for AI agents.
Generate architecture, database, or business flow diagrams from code using AI agents.