Fable 5 with omniglyph context compression — DUMPS | Hardcore Engineering

[Skip to main content](#main)

[![<<HC&>|$ENG](/static/hc-eng-logo.svg)](/) 

[HOME](/) [SERVICES](/services) [ARTICLES](/articles) [DUMPS](/dumps) [APPS](/apps) [ABOUT](/about) 

CMD: 0 // CLK: 0 // KEY: 0 // 

take 2026-07-26 by Stephan Schielke / f59bf179 / [llm.md](/dumps/fable5-with-omniglyph-context-compression.md) 

# Fable 5 with omniglyph context compression

#ai #llm #context #compression 

## [](#a-picture-is-worth-a-thousand-words)A picture is worth a thousand words

That old proverb was a lossy compression claim all along! A thousand words of prose collapse into one image your brain decodes in a glance. LLMs can do the same trick, and the savings are absurd.

I have been squeezing agent context for a while and in my [Compress Yourself Token Rich](/articles/caveman-cut-ai-token-costs) article I hinted at the possibilities of finding a better standard for lossless text compression. Although not lossless, omniglyph takes the next step and compresses whole context blocks into an **image** and feeds that to a vision-capable model:

![omniglyph example render](/static/images/dumps/omniglyph-example-render.png)

[@omniglyph](https://www.npmjs.com/package/omniglyph) example rendering of context as an image. 

## [](#why-the-image-vector-space-packs-more-in)Why the image vector space packs more in

A block of API docs, config, and log records is expensive as text: every word, brace, and UUID becomes tokens. Render that same block as a compact image and a vision model reads it from a **much denser latent space**, because the image is projected into a handful of vision embeddings instead of hundreds of text tokens. Same information, a fraction of the token budget.

The screenshot below shows my compression pipeline and token savings using [@omniglyph](https://www.npmjs.com/package/omniglyph):

![OmniRoute omniglyph dashboard showing a full tool-spec, config, and ledger-record page compressed to roughly 84 tokens](/static/images/dumps/fable5-with-omniglyph-context-as-image-compression.png)

Omniglyph context compression logs from my [OmniRoute](https://omnirouter.up-to-the.cloud) gateway. A whole context page rendered as one image, ≈ 84 tokens. 

Going from 150k tokens per request to just 50k really is not bad at all.

## [](#the-library-doing-the-heavy-lifting)The library doing the heavy lifting

The text-to-image encoding leans on [pxpipe](https://github.com/teamchong/pxpipe), a tidy library for packing text into images (and back) so the pixels carry the payload. Pair it with a vision model on the read side and you have a working context-compression pipeline: text in, image on the wire, meaning out.

Same idea as caveman, one layer deeper: caveman shrinks the *words*, omniglyph shrinks the *representation*. Stack both and the machine-to-machine layers stop paying human-language prices.

## [](#want-these-savings-on-your-stack)Want these savings on your stack?

Omniglyph is not a toy. It is real token budget back in your pocket, faster inference, and more agents per subscription. If you want image-vector context compression wired into your own agents and gateways, that is exactly the kind of work I do.

[Book my services](/services) and let us cut your context bill the same way. A picture really is worth a thousand tokens. 

keyboard\_command\_key

/search for stuff Send a prompt to my LLMs /summarize a page Open a chat Use a /command Send a /dm to my phone Ask the /chat assistant Smash your head against the keyboard Hire me /search for stuff 

... 

CTRL+K