Netflix Engineer Open-Sources Headroom, Cuts Agent Token Use by Up to 95%
Roger_M_Taylor · x · 2026-09-12
A Netflix engineer has open-sourced Headroom, a compression layer that sits between coding agents and LLMs. JSON, code, logs, and RAG chunks each get a specialized compressor; originals stay local so compression is reversible.
- Cuts tokens 60-95% for JSON and 20% for coding agents with no accuracy loss and zero code changes
- Setup: pip install "headroom-ai[all]" then headroom wrap claude
- Works with Claude Code, Cursor, Codex, and OpenAI-compatible APIs; ships as a library, proxy, and MCP server, fully local
The repo has reached 71.6k stars on GitHub.
More from coding & agent
- Limma MCP structures unstructured data end-to-end so agents never miss a detail — FlimsyIngenuity7248 · 2026-10-31
- Agent audit metric: can you name which tests ran and files changed without reading its summary? — ronbodkin · 2026-10-31
- FlowSense MCP lets Claude Code inspect and firewall your Mac's network traffic locally — hani_q · 2026-10-31
- Dev: coding agent notifications only worth pushing when waiting on approval — petrusenko_max · 2026-10-31
- Unofficial OpenTargets MCP Server Brings Gene-Drug-Disease Data to LLMs — modelcontextprotocol · 2026-10-31
- zero-core-budget MCP Connector Adds Spending and ROI Tracking for Agents — modelcontextprotocol · 2026-10-31