Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
//! headroom-proxy library: transparent reverse proxy in front of the Python
//! Headroom proxy. Used by both `main.rs` and the integration tests.
#![forbid(unsafe_code)]
pub mod bedrock;
pub mod cache_stabilization;
pub mod compression;
pub mod config;
pub mod error;
pub mod handlers;
pub mod headers;
pub mod health;
pub mod observability;
pub mod proxy;
pub mod responses_items;
pub mod sse;
pub mod tls;
pub mod upstream_path;
pub mod vertex;
pub mod websocket;
pub use config::Config;
pub use error::ProxyError;
pub use proxy::{build_app, AppState};