#API

torchmd

torchmd

★ 719

End-To-End Molecular Dynamics (MD) Engine using PyTorch

kadevin

ilab-conjure

★ 718

GPT-image-2 AI WebUI Codex Responses OpenAI API Chip An AI image generation WebUI workbench for GPT-image-2 with Codex Responses and OpenAI-compatible API support, shared gallery references, multi-type quick chips, prompt templates, concurrent tasks, and local queue management.

bkingfilm

lapian-notes

★ 718

AI-assisted film breakdown notebook: story-lane timeline, structure tree, emotion curve, write notes while you watch. Free, open source, fully local.

agarwalvishal

claude-chat-exporter

★ 717

One-click, privacy-first exporter for Claude.ai chats — clean Markdown with artifacts and attachments, ready for Obsidian and RAG.

xichan96

dinotty

★ 716

Multi-device terminal server for AI coding agents. Server-side VTE, session persistence, file browser, web preview, plugin system. Self-hosted.

pegainfer-project

pegainfer

★ 716

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

XiaomiRobotics

Xiaomi-Robotics-1

★ 714

Code for Xiaomi-Robotics-1

basler

pypylon

★ 714

The official Python language binding for the Basler pylon C++ APIs

JimLiu

Illustrated-Agent-Skills

★ 714

Official repo for Illustrated Skill: A Practical Guide to Boosting AI Productivity

whitelonng

dshcode

★ 713

Community desktop companion for DeepSeek Harness — one-click Electron app for macOS and Windows

openai

openai-cli

★ 713

Official CLI for the OpenAI API

Obiente

native

★ 711

Adaptive native Nextcloud client for mobile and desktop, with dynamic support for the wider Nextcloud app ecosystem.

michaelthwan

searchGPT

★ 711

Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.

instavm

clickclickclick

★ 711

Autonomous Android and computer use using any LLM (local or remote)

iamtelescope

telescope

★ 711

Web-based log viewer UI. Explore logs data stored in several sources: ClickHouse, Kubernetes or Docker

FireRedTeam

FireRedASR2S

★ 710

A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.

MarioSieg

magnetron

★ 709

A zero-dependency ML framework in C with a modern Python API for full control over execution and memory.

perpetual-ml

perpetual

★ 708

Perpetual is a high-performance gradient boosting machine. It delivers optimal accuracy in a single run without complex tuning through a simple budget parameter. It features out-of-the-box support for causal ML, continual learning, native calibration, and robust drift monitoring, along with Rust core and zero-copy bindings for Python and R

alinaqi

maggy

★ 707

What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center

ARahim3

mlx-dspark

★ 707

Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.