Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Benchmarks for Testing Narrative Understanding

Manuscript source: Self-orthogonalizing attractor neural networks emerging from the free energy principle

[ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

onpair compression

Generate any location from the real world in Minecraft with a high level of detail.

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

State-of-the-art TTS model under 25MB 😻

Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)

The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.

A tool to snap pixels to a perfect grid. Designed to fix messy and inconsistent pixel art generated by AI.

A fast and soft pattern search for trillion-scale corpora.

Official code and pretrained models for Linear Consistency Autoencoders (Lin-CAE), a method to induce linearity in audio autoencoders via data augmentation.

Monospaced bitmap fonts

Microsoft Software Download Listing

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

Exploration of Cloudflare D1/KV/Cache latencies

The visual feedback tool for agents.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

TLX - A Collection of Sophisticated C++ Data Structures, Algorithms, and Miscellaneous Helpers

A compact, efficient Prolog interpreter written in plain old C.

Go library implementing binary fuse and xor filters

Soprano: Instant, Ultra-Realistic Text-to-Speech

Zero-copy PDF text extraction library written in Zig. High-performance, memory-mapped parsing with SIMD acceleration.

Lightweight Linked Data Server and Proxy

Build ultra fast, tiny, and cross-platform desktop apps with Typescript.

FlashInfer: Kernel Library for LLM Serving

A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.