GitHub trending

parvbhullar/unpod

Wordpress for Voice AI.

vishhnuprasath-p/Traffic-Surveillance-LPR

Traffic Surveillance System using YOLOv8 and EasyOCR with document validation

xiaguan/pegainfer

Pure Rust + CUDA LLM inference engine

Daewooki/simple-shorts-generator

단순한 구조의 숏츠 자동 생성 도구입니다.

ealicesora/awesome-video-forcing

Collection of forcing related autoregressive video Gen

paidinesh7/team-financial-analyst

Two-stage financial analysis workflow — executive briefing first, detailed deep dive on request

akumaburn/RobinLLM

Robin LLM is a Java-based service that crawls OpenRouter's website for free LLM models, continuously tests their performance, and provides an OpenAI-compatible API that automatically routes requests to the best-performing available free model.

ShaunTsai/skill-google-calendar

A Kiro agent skill that syncs Google Calendar events for schedule awareness

rdilip/apt

Adaptive tokenization for proteins

max-muoto/monty-dspy-rlm

Example for a Monty-enabled RLM in DSPy

zeyuji/LLM-PeerReview

panda850819/murmur-voice

Your voice, unheard by others. Privacy-first voice-to-text for macOS, built with Rust.

zhaochenyang20/sglang-diffusion-routing

A demonstrative example of running SGLang Diffusion with DP router

Belluxx/Perplex

Analyze how "surprised" LLMs are when reading a piece of text

HariniSelvam-cse/AI-Healthcare-Prediction-Dashboard

AI-powered healthcare dashboard using Streamlit that integrates drug recommendation and symptom-based disease prediction with multi-model ML comparison and interactive visualizations.

Xinyang-Zhao/RAIFE

RAIFE is a high-performance Rust pipeline for medical image analysis. Implements rapid NIfTI ingestion, preprocessing, and 2.5D stacking for BraTS-2018. Includes benchmarks demonstrating superior speed over MONAI workflows.

yuanxiaochenAC/MamiHealth.AI

MamiHealth is an AI-powered nutrition companion for people managing chronic conditions, weight goals, or fast-paced urban lifestyles. By turning a simple pre-meal photo into a personalized health decision moment, it replaces manual calorie tracking with intelligent, real-time guidance.爱你妈咪是一款以“饭前拍照”为核心入口的 AI 饮食健康管理应用，面向慢性病人群、减重用户及外卖依赖者。

seanhan19911990-source/LTX2EasyPrompt-LD

A ComfyUI custom node that turns plain English descriptions into fully structured, cinema-ready prompts for LTX-2 video generation — powered by a local, uncensored LLM with zero internet dependency after setup.

fars-analemma/transferable-defensive-tokens

lyramakesmusic/activations-vis

manelsen/redclaw

CoderofTheWest/openclaw-plugin-continuity

Infinite Thread — persistent, intelligent memory for OpenClaw agents

lachameleon/epstein-llm

The Epstein Island LLM with a built in inference tool

Rainyrou/ASTER

ASTER: Agentic Scaling with Tool-integrated Extended Reasoning

vukrosic/latent-topological-contraction-reasoning

Paper and experiments for reasoning by repeatedly refining a latent state.

DevvGwardo/grok-imagine-video

Video generation skill for OpenClaw. Text-to-video, image-to-video, and video editing via natural language using xAI's Grok Imagine API.

preacherwhite/ODE-GS

[ICLR 2026] ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting

Weather-719/astrbot_plugin_Gemini_STT

这是一个面向 AstrBot 的 Gemini 语音桥接插件。它会优先识别语音消息，将 silk/amr/wav/mp3 自动转换并转写为文本，再交由框架按正常会话链路继续回复，实现“语音≈自动打字”的体验。插件本身不抢人格回复，支持群聊白名单、失败策略（放行/拦截/提示）、简洁或详细输出、模型名自动清洗、语音来源与说话人信息附加等配置，适合复杂插件生态下稳定接入语音能力

CoworkedShawn/openclaw-skills

Custom OpenClaw skills for AI agent capabilities - memory systems, prompt injection defense, intent routing, and platform integrations

modu-ai/smart-cowork-life

슬기로운 코워크 생활 — 스타트업, 직장인, 취준생을 위한 한국형 업무 스킬 플러그인 (Claude Cowork)

KimYx0207/agent-teams-playbook

Agent Teams编排Skill

Paitesanshi/ClawBoss

AI productivity coach for OpenClaw — not a task manager, but a coach who cares. No one is your boss except yourself.

ronantakizawa/lorashare

Python Library for running SHARE (Compress multiple LoRA adapters into a shared subspace)

xxtluuu/openclaw-sensevoice

⚡ Offline speech-to-text plugin for OpenClaw — 1s cold start, 228MB model, Chinese-optimized. Powered by SenseVoice + Rust + ONNX Runtime. 离线语音转文字插件，秒级响应，中文优化，支持中/英/日/韩/粤五语。

rullerzhou-afk/bring-4o-home

把 4o 搬回家，一个开源的私人 AI 聊天界面

glouppe/miniature

wrkhard/driftax

JAX implementation of https://arxiv.org/abs/2602.04770

slopism/manifesto

The Slopism manifesto, generated through democratic collaboration between 5 AI models and 1 human curator. Every step documented.

zhouzhou98/ai_interview

ai智能辅助面试

kothapavan1998/deeprecall

Recursive reasoning engine for AI agents and vector databases. Powered by MIT's RLM.

gracefulning/CoopLLM-Cache

Official implementation of "Cooperative Edge Caching with Large Language Model in Wireless Networks".

rynn-k/Bing-Create

A REST API wrapper for Bing Image Creator — supports DALL-E, GPT-4o, and MAI Image 1 with image & video generation.

Jinl2l3/ai-pick-cloud

基于AI大模型的本地照片/视频智能整理工具

konsti-web/hytalecraft

HytaleCraft - AI-powered text-to-3D-blocks pipeline for Hytale. Generate 3D models from text prompts and place them as blocks in your world.

gyunggyung/Open-Yaongi

52 Layers 4B(0.6B Active) MoE | Nemotron-3 Style + Teon Optimizer + Mamba-2 SSM + FP8 Training on H100

omarbadrani/Vision-AI-Pro---Professional-Object-Detection-Platform

Vision AI Pro is a sophisticated computer vision application that transforms how businesses and developers interact with object detection technology. Built on Ultralytics' state-of-the-art YOLOv8 architecture, this platform delivers enterprise-grade performance with an exceptionally polished user experience.

anup-singhai/v16

Autonomous personal assistant for everyone

Xinkai/dictype

Real-time voice-to-text input on Linux.

igor-silveira/Pincer

A self-hosted, security-first AI assistant gateway written in Go. Pincer connects to messaging platforms, executes real-world tasks through sandboxed tools, and manages long-running conversations with persistent memory - all from a single binary.

qkrwnduf1997/HPSG

Official implementation of **HPSG (Human Preference and Success-based Grasping)**, a deep reinforcement learning framework for **end-to-end 4-DoF robotic grasping from RGB-D observations**.

pbantolas/liftosaur-program-creator

A liftoscript skill for AI agents. Useful when creating custom Liftosaur programs.

briansunter/z-cli

ariannamethod/molecule

molecule.ai

malik-builds/SixtySevenDetector

Real-time gesture detection system using YOLO-Pose to trigger multimedia responses and track performance analytics.

knoxryder323/Fullstack-MERN-generative-AI-Project-GenzAI-

maifeipin/EdgeTTSPlayer

基于 edge-tts 的文本转语音工具，支持流式播放和MP3导出

MiltonLoop/milton-loop

AlphaZero-inspired chess engine with MCTS self-play, neural network training, and Lichess bot integration

knoxryder323/gpt-neo

tyeom/panda-bot

claude Code subprocess / Anthropic api 기반 Agent

david-xinyuwei/EXAONE-Multi-LoRA-on-Azure