ctrlb-decompose - Strip noise from logs for LLM-ready insights
Show HN: Ctrlb-decompose: Strip the noise from logs before sending to LLMs
ctrlb-decompose transforms millions of noisy log lines into a handful of actionable, structured patterns optimized for Large Language Models. By utilizing a two-stage pipeline featuring CLP encoding and Drain3 clustering, this Rust-based tool compresses raw logs while preserving critical statistics, anomalies, and variable correlations. Whether run as a CLI, a WASM module in the browser, or a library, it delivers token-efficient markdown or JSON output, enabling developers to feed clean, high-signal data directly into AI agents for rapid debugging and analysis.
Turn millions of noisy log lines into a handful of actionable patterns — with typed variables, quantile stats, anomaly flags, and severity scoring.