token reduction

Headroom is an open-source context compression layer for AI agents. It compresses tool outputs, logs, files, RAG chunks, and conversation history before they reach the LLM, with support for a library, proxy, and MCP server.

Turo is a CLI proxy that reduces prompt text to content words to save tokens for coding agents. The repo shows install options, command examples, and support for multiple agents and modes.

An in-memory Tree-sitter AST pruning and context firewall MCP server for coding agents like Cursor and Claude. The repo includes installation steps, diagnostics, benchmarks, and a clear usage path for local setup.

A local gateway for Claude Code that logs tool calls, enforces approval rules, and trims noisy tool output to save tokens.

Go-native CLI proxy that reduces noisy command output before it reaches an LLM context, with retention checks, exit-code preservation, and token-saving history.

A local Rust-plus-Python middleware layer for LLM apps that claims to reduce token usage and add in-process security checks before prompts are sent to a provider.

Local-first Python SDK for AI agents that compresses web pages before LLM use, flattens Shadow DOM, builds action maps, and extracts structured data from tables, forms, and lists.