pixrep
Hey HN, creator here. I've been experimenting heavily with large-context multimodal LLMs (like Gemini 3 Pro) for coding tasks. I noticed that feeding raw text files consumes a massive amount of tokens and often clutters the context window. Inspired by recent research (like the DeepSeek-OCR paper) suggesting visual encoders can be more efficient than text tokenizers for structured data, I built pixrep. It’s a CLI tool that converts your codebase into a structured, syntax-highlighted PDF hierarchy. Key features: - Token Efficiency: In my local benchmark, a repo requiring ~31k text tokens was…
pixrep launched on March 7, 2026 with 2 votes, #5,166 of 23,380 launches that month.
What it does
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.
Let LLMs see your codebase just like you do. Contribute to TingjiaInFuture/pixrep development by creating an account on GitHub.
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: Traditional text tokenization is expensive. Visual encoding compresses structure efficiently. Verdict: In the multimodal era, the optimal way to feed code is via "visual perception" rather than "text reading." pip install " pixrep[png] " 🛠️ Usage Quick Start Convert the current directory to hierarchial PDFs in ./pixrep_output/<repo_name> : pixrep . Or pack everything into a single, token-optimized PDF…from github.com
In the maker’s words, at launch
Hey HN, creator here. I've been experimenting heavily with large-context multimodal LLMs (like Gemini 3 Pro) for coding tasks. I noticed that feeding raw text files consumes a massive amount of tokens and often clutters the context window. Inspired by recent research (like the DeepSeek-OCR paper) suggesting visual…
Does a similar job
all alternatives →
Pi Coding AgentMay 2026 · pi.dev · ▲176A new Emacs mode for AI-assisted coding (Claude Code style), with native Emacs buffers instead of a flickering terminal. Built on top of pi, a no-bs open source Claude Code alternative. It supports Claude, GPT, Gemini, Ollama. I've been using it daily for weeks. Demo video that says more than $NUMBER words: https://danielnouri.org/media/pi-coding-agent-demo.mp4 The key decision here is that we have two separate windows: chat history is a markdown-mode buffer, with beautiful rendering, unlimted scrollback, selective tool expansion where it matters, etc. The input window…
Chonkie – A Fast, Lightweight Text Chunking Library for RAG2024 · github.com · ▲199I built Chonkie because I was tired of rewriting chunking code for RAG applications. Existing libraries were either too bloated (80MB+) or too basic, with no middle ground. Core features: - 21MB default install vs 80-171MB alternatives - 33x faster token chunking than popular alternatives - Supports multiple chunking strategies: token, word, sentence, and semantic - Works with all major tokenizers (transformers, tokenizers, tiktoken) - Zero external dependencies for basic functionality Technical optimizations: - Uses tiktoken with multi-threading for faster tokenization - Implements…
Fully client-side GPT2 prediction visualizer2023 · perplexity.vercel.app · ▲153Hi HN! I've found this visualization tool immensely helpful over the years for getting an intuition for how an LLM "sees" some piece of text, and with a bit of elbow grease decided to move all compute to client side so I could make it publicly available. I've found it particularly useful for - Understanding exactly how repetition and patterns affect a small LM's ability to predict correctly - Understanding different tokenization patterns and how it affects model output - Getting a general sense of how "hard" different prediction tasks are for GPT-style models Known problems (that I probably…
Badge that shows how well your codebase fits in an LLM's context windowFeb 2026 · github.com · ▲88Small codebases were always a good thing. With coding agents, there's now a huge advantage to having a codebase small enough that an agent can hold the full thing in context. Repo Tokens is a GitHub Action that counts your codebase's size in tokens (using tiktoken) and updates a badge in your README. The badge color reflects what percentage of an LLM's context window the codebase fills: green for under 30%, yellow for 50-70%, red for 70%+. Context window size is configurable and defaults to 200k (size of Claude models). It's a composite action. Installs tiktoken, runs ~60 lines of inline…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
