Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation

Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.

Helping coding agents never make mistakes working with public or private libraries without wasting the context window.