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
Update README with dashboard info and installation recommendations
chopratejasf3e03f165252
diff --git a/README.md b/README.mdindex 1e33b914b..55cc2fdf6 100644--- a/README.md+++ b/README.md@@ -202,10 +202,14 @@ For deep technical details, see [Architecture Documentation](docs/ARCHITECTURE.m### Option 1: Proxy (Zero Code Changes)```bash-pip install "headroom-ai[proxy]"+pip install "headroom-ai[all]" # Recommended for best performanceheadroom proxy --port 8787```+> **Note:** First startup downloads ML models (~500MB) for optimal compression. This is a one-time download.++**Dashboard:** Open http://localhost:8787/dashboard to see real-time stats, token savings, and request history.+Point your tools at the proxy:```bash@@ -434,6 +438,10 @@ New models auto-supported via naming pattern detection.## Installation```bash+# Recommended: Install everything for best compression performance+pip install "headroom-ai[all]"++# Or install specific componentspip install headroom-ai # SDK onlypip install "headroom-ai[proxy]" # Proxy serverpip install "headroom-ai[langchain]" # LangChain integration@@ -441,11 +449,12 @@ pip install "headroom-ai[agno]" # Agno agent frameworkpip install "headroom-ai[evals]" # Evaluation frameworkpip install "headroom-ai[code]" # AST-based code compressionpip install "headroom-ai[llmlingua]" # ML-based compression-pip install "headroom-ai[all]" # Everything```**Requirements**: Python 3.10++> **First-time startup:** Headroom downloads ML models (~500MB) on first run for optimal compression. This is cached locally and only happens once.+---## Documentation