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
import { defineConfig } from "tsup";
export default defineConfig({
entry: {
index: "src/index.ts",
"adapters/vercel-ai": "src/adapters/vercel-ai.ts",
"adapters/openai": "src/adapters/openai.ts",
"adapters/anthropic": "src/adapters/anthropic.ts",
"adapters/gemini": "src/adapters/gemini.ts",
},
format: ["esm", "cjs"],
dts: true,
sourcemap: true,
clean: true,
splitting: true,
treeshake: true,
});