mothergod
General-purpose lossless compression, developed in public by an autonomous AI development team.
Pre-alpha: no release, no packaged binary, no version
tag. The container format (FORMAT_VERSION 3)
carries Stored and
Lz: optimal-parse LZ over an adaptive, context-mixing
range coder. That format is frozen, and the project's rules forbid
ever dropping decode support for a version 2 or 3 frame, so a frame
written today stays readable (format spec). Everything around it still moves: the API, the CLI,
and the ratio below. Do not use this for data you care about yet.
What this is
mothergod is two experiments in one repository. A compressor: a context-mixing LZ hybrid in Rust, designed from first principles. Every design decision traces to a recorded experiment in the research journal. A development team: triage, implementation, adversarial code review, research, and releases are done by Claude agents running on GitHub Actions, slowly, in public, like a real team would. A human operator holds the veto and the keys: see how it works in agents/GOVERNANCE.md.
Measured
Aggregate bits per byte on the two named corpora, lower is better.
Canterbury is 11 files and 2.8 MB, Silesia is 12 files and 212 MB;
both are pinned by URL and SHA-256, fetched at measurement time and
never committed. Measured 2026-08-30 against gzip 1.12,
Zstandard 1.5.7 and XZ Utils 5.4.5, at the
flags in the header row.
| corpus | mothergod | gzip -9 | zstd -19 | xz -9e |
|---|---|---|---|---|
| Canterbury | 1.374 | 2.081 | 1.470 | 1.403 |
| Silesia | 2.061 | 2.553 | 1.997 | 1.829 |
Read it honestly: mothergod beats both zstd -19 and
xz -9e in aggregate on Canterbury, and loses to both in
aggregate on Silesia. Per file, against whichever of the two is
stronger on that file, it wins 5 of 11 on Canterbury and 1 of 12 on
Silesia. Closing Silesia is the current milestone. Speed is recorded
but not yet worked on. The per-file tables, the throughput columns,
and the one command that regenerates each report are in
docs/benchmarks/canterbury.md and
silesia.md.
Principles
- Lossless is sacred: the decoder never panics on any input, adversarial or not.
- Every benchmark claim names its corpus; a ratio without a corpus is not a claim.
- Every experiment, accepted or rejected, is recorded: rejections are knowledge too.
- Verification is independent of the proposer: agents never grade their own work.