Proprietary Semantic Compression

Compress Meaning,
Not Bytes

LoreTokens are an AI-native format that lets models work on compact meaning instead of raw data. One line encodes what pages of JSON cannot.

113:1
Compression Ratio
94.9% storage reduction
616x
Faster Than PostgreSQL
SAIQL on same hardware
200K+
Records In Production
Firefox, Chromium, Linux kernel
Why LoreTokens

Built For How Models Think

Instead of squeezing bytes, LoreTokens compress meaning. Regular, symbolic, and explicit -- the way language models already process information.

S

Semantic Compression

A single line encodes domain, concept, fields, and output shape. Modern LLMs expand it back into full detail on demand.

D

Deterministic Retrieval

Atlas uses LoreTokens for exact recall across entire codebases. Nothing is approximated, nothing degrades at scale.

N

AI-Native Format

No decompression step. The compressed form IS the usable form. Models read LoreTokens directly -- no parsing overhead, no information loss.

Format Tiers

Three Densities, One Format

Choose the density that fits the use case. All three tiers are interchangeable and convert losslessly between each other.

U

Ultra (.ltu)

Human-friendly. For documentation, audits, and exported knowledge where clarity matters more than density.

S

Standard (.lt)

Balanced. For CLI tools, diffs, repos, and day-to-day use. Compact but still readable.

G

Symbolic (.sym)

Machine-centric. Maximum compression for hot paths, GPU hooks, and high-throughput pipelines.

Proprietary format. The LoreToken specification, glyph tables, GPU hook, and internal tooling are trade secrets. This page describes what LoreTokens achieve, not how they work internally.

The Foundation Under Everything

Every product in the stack runs on LoreTokens.

See It In Action

LoreTokens power the entire ShipItClean adversarial code review platform and the SAIQL database engine.

ShipItClean Explore SAIQL