💾 Self-hosted online file converter. Supports 1000+ formats ⚙️

OpenSource ngrok alternative.

The framework for AI souls

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.

Open Vision Agents by Stream. Build Vision Agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Living memory for AI

VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning

Open-Source Frontier Voice AI

Controllable and fast Text-to-Speech for over 7000 languages!

On-device TTS model by Neuphonic

Connect your devices into a secure WireGuard®-based overlay network with SSO, MFA and granular access controls.

cocoon

Toolkit for linearizing PDFs for LLM datasets/training

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

Contexts Optical Compression

YugabyteDB - the cloud native distributed SQL database for mission-critical applications.

EGGROLL in C, integer-first training

A JavaScript library for providing multiple simultaneous, stable, fault-tolerant and resumable/restartable uploads via the HTML5 File API.

An open source utility that provides fast incremental file transfer. It also has useful features for backup and restore operations among many other use cases.

Simple .NET library capable of tracking users across re-installs and hardware components swapping, and even entirely new computer using the neighborhood's network endpoints.

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

StreamingVLM: Real-Time Understanding for Infinite Video Streams

Beads - A memory upgrade for your coding agent

Mapsui is a .NET Map component for: MAUI, Avalonia, Uno Platform, Blazor, WPF, WinUI, Windows Forms, Eto Forms, .NET for Android and .NET for iOS

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

Wan: Open and Advanced Large-Scale Video Generative Models