Compress logs for LLM analysis — Rust-powered, Python API. 40-60% token savings.

High-ratio JSONL compressor with block-level random access. ~9% ratio on log data - compression smaller than gzip/zstd. Cut S3 storage and egress costs. Free for personal and open-source use.

MCP server that cuts Claude Code token usage: log compression (builds/tests/installs) + smart file reading (symbol-level source access via tree-sitter).

Extract the essence of massive logs - fold repetitive noise, show unique patterns. Feed cleaner context to LLMs and coding agents.

Convert any compressed JSONL archive to PFC cold storage — from S3, Azure, GCS or local disk. No intermediate files, no schema changes, no pipelines.

DuckDB extension to read PFC-JSONL compressed log files with block-level timestamp filtering

Stream Fluent Bit logs directly to PFC-JSONL compressed archives (.pfc). Free for personal and open-source use.

Python interface for PFC-JSONL