AI product Open source
ctrlb-decompose is a log-processing tool from ctrlb that converts large, repetitive log files into compact, LLM-ready patterns with typed variables, quantiles, anomaly information, severity scores, and example values. Its single-pass pipeline extracts and normalizes timestamps, applies CLP encoding to replace integers, floats, IP addresses, and strings with compact placeholders, clusters log types with the tree-based Drain3 algorithm, and merges wildcard positions with decoded values for semantic typing such as IPv4, UUID, duration, enum, and integer. It accumulates DDSketch quantiles, HyperLogLog cardinality estimates, top-k values, temporal buckets, and reservoir-sampled lines, and provides human-readable and LLM-optimization output modes. The project runs as a CLI, a Rust library, or client-side WebAssembly in the browser; its README states that logs remain on the local machine.
1 use taken from transcripts — each links to the moment in the video.
Processes large log files in a streaming pass to identify recurring structural patterns instead of sending every line to a model. It normalizes variables, clusters messages, and adds typed fields, percentile statistics, anomaly flags, and severity scores.
1 in the library.