repoGitHubTrust 82 · PrimaryPublished 23h agoLive · 20h ago
headroomlabs-ai/headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Covers
Implements
Related across the graph
paperTraceLab: Characterizing Coding Agent Workloads for LLM ServingnewsI spent ~4.5 months building a free, self-hosted AI gateway: one endpoint for 237 providers (90+ free), auto-fallback, and a token-compression pipeline (MIT)news[R] Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost
