⬢github Python · 77.5K ★ +1.6K since we first saw it · pushed 2 h ago · Apache-2.0
headroomlabs-ai/headroom
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.
Headroom is a context compression layer for AI agents: it compresses tool outputs, logs, files, RAG chunks, and conversation history before they reach an LLM, cutting token usage (e.g. 60-95% for JSON) while preserving critical details like error lines. It ships as a Python/TypeScript library, a zero-code-change proxy, an agent wrapper CLI, and an MCP server, all running locally.
Why now: It's gaining attention as a #1 Trendshift repository, riding current interest in token-cost optimization and context engineering for coding agents like Claude Code and Cursor.
Who it is for: Developers building or running LLM agents who want to cut API token costs without changing their code or answers quality.
agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchain
Stars over our 296 snapshots: 76K to 77.5K, since 3 d ago.
Where people talked about it
- ⬢github headroomlabs-ai/headroom 6 h ago
API: https://socialmediatrends-api.osmike.com/v1/repos/headroomlabs-ai/headroom