Search

An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.

Convert PDF to markdown + JSON quickly with high accuracy

Optimize floating-point expressions for accuracy

accuracy-focused GBA BIOS replacement

FNA - Accuracy-focused XNA4 reimplementation for open platforms

Combines the high accuracy of AR with the scale of GPS data.

Teleprompter software for all video creators. Built with ease of use, productivity, control accuracy, and smooth performance in mind.

High accuracy RAG for answering questions from scientific documents with citations

Doing simple retrieval from LLM models at various context lengths to measure accuracy

📐 Fast token estimation with 95%+ average accuracy in a 2kB bundle

nnInteractive is a framework for 3D interactive segmentation, supporting intuitive prompts like points, scribbles, bounding boxes, and lasso. Trained on 120+ diverse 3D datasets, it sets a new standard in accuracy, usability, and adaptability for clinical and research applications.

A large collection of NES accuracy tests on a single NROM cartridge.

197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.

Speaker diarization in Rust with pyannote-level accuracy. 1790–5970x realtime on NVIDIA GPUs, 430–910x on Apple Silicon.

Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI.

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page.

1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy