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
chore(sdk-typescript): npm metadata and the proxy requirement up front (#4536)
Tejas Chopra6c3d7475077b
diff --git a/sdk/typescript/README.md b/sdk/typescript/README.mdindex 0d5eba03d..7d0453da9 100644--- a/sdk/typescript/README.md+++ b/sdk/typescript/README.md@@ -1,6 +1,16 @@-# headroom-ai+# Headroom (`headroom-ai`) for TypeScript-Compress LLM context. Save tokens. Fit more into every request.+Compress tool outputs, logs, JSON and chat history before each LLM call. Fewer+input tokens, same answers.++**Requires the Headroom proxy.** Compression runs in the Python proxy; this+package sends messages to it over HTTP (default `http://localhost:8787`). Start+it first:++```bash+pip install "headroom-ai[proxy]" # or: uv tool install --python 3.13 "headroom-ai[proxy]"+headroom proxy --port 8787+```## Install@@ -23,7 +33,7 @@ const response = await openai.chat.completions.create({});```-Requires a running Headroom proxy (`headroom proxy`).+Pass `baseUrl` if the proxy is not on `http://localhost:8787`.## Framework Adaptersdiff --git a/sdk/typescript/package.json b/sdk/typescript/package.jsonindex 28565e72f..096ead3ed 100644--- a/sdk/typescript/package.json+++ b/sdk/typescript/package.json@@ -1,7 +1,34 @@{"name": "headroom-ai","version": "0.42.0",- "description": "Compress LLM context. Save tokens. Fit more into every request.",+ "description": "Compress tool outputs, logs, JSON and chat history before each LLM call. Fewer input tokens, same answers. Adapters for OpenAI, Anthropic, Gemini and the Vercel AI SDK. Runs against the local Headroom proxy (pip install \"headroom-ai[proxy]\").",+ "keywords": [+ "llm",+ "openai",+ "anthropic",+ "gemini",+ "vercel-ai-sdk",+ "token-cost",+ "reduce-tokens",+ "input-tokens",+ "context-window",+ "token-budget",+ "tool-output",+ "chat-history",+ "context-compression",+ "prompt-compression",+ "agents",+ "mcp"+ ],+ "homepage": "https://docs.headroomlabs.ai/docs/quickstart",+ "repository": {+ "type": "git",+ "url": "git+https://github.com/headroomlabs-ai/headroom.git",+ "directory": "sdk/typescript"+ },+ "bugs": {+ "url": "https://github.com/headroomlabs-ai/headroom/issues"+ },"type": "module","main": "./dist/index.cjs","module": "./dist/index.js",