New User

pixrep - Let LLMs see your codebase just like you do.

by
pixrep is a developer tool designed to bridge the gap between large code repositories and Multimodal Large Language Models. Instead of feeding raw text that consumes massive context windows, pixrep converts your repository into a structured, hierarchical set of PDFs. This allows you to: 1.Save 90% Tokens: Visual encoding is far more efficient than text tokenization. 2.Test for Free: Easily share your entire codebase with premium models on platforms like arena.ai without hitting text limits.

Add a comment

Replies

Best
New User
Maker
📌
Hey PH. I'm Tingjia. I built Pixrep. It's open-source. The pain is simple. You paste code into ChatGPT or Claude. Structure gone. Architecture gone. Half your tokens wasted on garbage. The LLM never sees your codebase. It guesses. So I fixed it. Pixrep. One command. One PDF. Your entire repo, structured. Run pixrep on your project folder. Out comes a single PDF with a directory tree, an index, auto-generated UML and callgraphs for Python JS TS, lint heatmaps highlighting problems inline, and smart filtering that strips out git folders, binaries, and bloat automatically. No copy-paste hell. No wasted context. The LLM finally gets the full picture. Cleaner prompts in, smarter responses out. That simple. 100% open-source. Star on GitHub! Now I'm curious. How are you feeding code context to LLMs today? Drop your workflow.