Reviewing technical documentation is often a frustrating trade-off. Manual proofreading is slow and tedious, but feeding documentation to generic AI or cloud LLMs quickly turns into an engineering headache. Generic grammar checkers don't understand code syntax—they happily translate inline API parameters, rewrite code comments, or rename terms like principal to principle in your IAM guides. On top of that, unreleased features and internal architecture docs often cannot be sent to third-party cloud APIs due to privacy and compliance boundaries.
Over the past year, I built and ran a local-first, small-model review pipeline across an internal repository of roughly 380,000 characters of technical docs—designed specifically to protect code fences, respect custom terminology, and run entirely offline.
Following my earlier architecture post, a few folks asked if the code would be available. It originally started as a rough internal script that was "just good enough for us," so I spent the past few months cleaning it up, decoupling it from our private setup, and adding tests. Today, DocSifter is open source under the MIT license, and I hope it serves as a helpful reference for teams tackling similar challenges.
DocSifter is now open source under the MIT license.
For a quick look at the complete workflow, open the interactive product story.