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
export { default, registerHeadroomPlugin } from "./plugin/index.js";
export { HeadroomContextEngine } from "./engine.js";
export { ProxyManager, normalizeAndValidateProxyUrl, isLocalProxyUrl, defaultLogger, probeHeadroomProxy } from "./proxy-manager.js";
export { agentToOpenAI, normalizeAgentMessages, openAIToAgent } from "./convert.js";
export { createHeadroomRetrieveTool } from "./tools/headroom-retrieve.js";
export {
DEFAULT_GATEWAY_PROVIDER_IDS,
applyGatewayProviderBaseUrls,
applyGatewayProviderBaseUrlsInPlace,
resolveGatewayProviderIds,
} from "./gateway-config.js";