Headroom Ships Context Compression With Accuracy Deltas Attached — 92% Token Cut on Code Search, GSM8K Unchanged at 0.870
headroomlabs-ai/headroom (62,876 stars, ~313/day) compresses tool outputs, logs, RAG chunks and files before they reach the model, and unusually publishes the accuracy side of the trade: GSM8K holds at 0.870 (±0.000), TruthfulQA actually improves 0.530 → 0.560, and SQuAD v2 plus BFCL retain 97%. Real workloads show 92% savings on code search (17,765 → 1,408 tokens), 92% on SRE debugging and 73% on GitHub issue triage. The three-stage pipeline routes by content type into SmartCrusher (JSON), an AST-aware CodeCompressor covering Python/JS/TS/Go/Rust/Java/C/C++/Perl, or a trained Kompress-v2-base model for prose — and a CacheAligner deliberately preserves provider KV-cache prefixes so compression doesn't destroy prompt caching. Ships as library, proxy (`headroom proxy --port 8787`) or MCP server.
Source
↳ Follow the thread