# Token Optimization

Context compression for LLM apps and coding agents

Headroom is an Apache-2.0 context compression layer for LLM apps and coding agents. It compresses tool output, logs, files, RAG chunks, and agent history through a local library, proxy, wrapper, or MCP server, with retrieval hooks for bringing originals back when needed. Treat its savings numbers as Headroom-reported benchmarks, not independent aicoolies measurements.

Turn any MCP server, OpenAPI spec, or GraphQL endpoint into a CLI — at runtime, with zero codegen.

mcp2cli turns MCP servers, OpenAPI specs, and GraphQL endpoints into standard CLIs at runtime — no codegen, no schema bloat. Tools and arguments load only when requested via --list and --help flags, cutting up to 96–99% of the tokens that native MCP integrations waste on schema preloading. Works with Claude Code, Cursor, Codex, and any agent that can call shell commands, and ships with OAuth, stdio/HTTP/SSE transports, and a bake mode for reusable connections.

CLI token usage tracker for AI coding agents

Tokscale is a CLI tool that tracks token usage and costs across AI coding agents including Claude Code, Codex, OpenCode, Gemini CLI, Cursor, and more. Built with a native Rust core for high-performance processing, it provides detailed breakdowns of input, output, cache, and reasoning tokens with real-time pricing calculations via LiteLLM data. Features include interactive 2D/3D contribution graphs, web visualization dashboards, global leaderboards, and JSON export for cost analysis.