GitHub Repository

An LLM code exploration token optimizer that runs in a Hyperdimensional Compute MCP server

11 starsZig

Opty – A Zig-based HDC that reduces token use by up to 90%

Name: Opty – A Zig-based HDC that reduces token use by up to 90%
Availability: InStock
Author: bojo

by bojo·Feb 25, 2026·4 points·4 comments

Visit Project View on HN

AI Analysis

●MidBig BrainWizardry

93% token reduction via HDC encoding, but claims unverified on large codebases beyond self-audit.

Strengths

•Hyperdimensional Computing + bind/bundle algebra is legitimately non-obvious and elegant approach
•TOON format output (30-60% fewer tokens than JSON) applies clever syntax optimization
•<1ms similarity search on 10,000-bit hypervectors is theoretically fast

Weaknesses

•Single self-audit benchmark on own codebase; no third-party validation or real-world large project results
•No MCP integration examples or user reports; 0 stars suggests zero adoption signal at publication

Post Description

I kept seeing people all over social media talking about how they were making custom local-LLM systems to help reduce the token load injected into their context window.

On the side my recent project has me looking at Hyperdimensional Distributed Memory. I couldn't help but wonder if I could make an MCP server to improve token usage. Sure enough, using a combination of HDC + TOOL format, I was able to get opty's own self audit down by 93% in token usage.

Still experimenting with large codebases but feel pretty good about how this should drive overall token usage down.

Happy to hear any feedback.