:woman: Library for image processing
- image-processing
- image-manipulation
- canvas
- javascript
111,821 visible repositories in the index
745–768 of 872 · Most stars
:woman: Library for image processing
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
oneAPI Data Analytics Library (oneDAL)
A Rust port of parinfer.
:white_check_mark: .NET crypto done right. Professionally audited.
The open-source, self-hosted video conferencing software. Scalable, customizable, and with a powerful AI Meeting Agent.
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
🔥🔥 The extremely fast inference engine for decision model
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.
Official Implementation of Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agents
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
📹 Open-source, self-hosted WebRTC 1-to-1 video calling for private real-time communication. Build secure browser-based consultations, coaching, support, telehealth, and other video call experiences with peer-to-peer communication and screen sharing.
SCENIC is an R package to infer Gene Regulatory Networks and cell types from single-cell RNA-seq data.
The unofficial conference app for DroidKaigi 2018 Tokyo
ceejbot's talk from JSConfEU 2019
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.
An open-source columnar data format designed for fast & realtime analytic with big data.
AI Agent Identity and Access Management and Inference Firewall
🧱 Experimental library for building inference engines
Presentations from H2O meetups & conferences by the H2O.ai team
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.
🏹 Parse JSON with style
[MIRROR] unofficial implementation of Dante protocol (Audio over IP)