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
Add demo GIF to README
Tejas Chopra029ca7d7e8db
diff --git a/Headroom-2.gif b/Headroom-2.gifnew file mode 100644index 000000000..95773b879Binary files /dev/null and b/Headroom-2.gif differdiff --git a/README.md b/README.mdindex dac9ddd58..48331e482 100644--- a/README.md+++ b/README.md@@ -31,7 +31,9 @@## Demo-**[Watch Headroom in action](https://github.com/chopratejas/headroom/releases/download/v0.2.15/Headroom.-.Optimized.mp4)** - Analyzing its own codebase with Claude Code while demonstrating real-time token savings with multi-tool agents.+<p align="center">+ <img src="Headroom-2.gif" alt="Headroom Demo" width="800">+</p>---