Stars
A unified way to get AI model info from various providers
A TTS model capable of generating ultra-realistic dialogue in one pass.
Project about an air quality monitor with e-paper display and ESP32-S3 for integration into ESPHome in Home Assistant.
Firmware installer: https://yashmulgaonkar.github.io/halo/
Convert ebooks to audiobooks with chapters and metadata using dynamic AI models and voice cloning. Supports 1,107+ languages!
Give Cursor Agent an AI Team and Advanced Skills
React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic last-mile 🪁
Convert PDF to markdown + JSON quickly with high accuracy
The Knowledge Platform - expedite delivery of your knowledge to AI. Build, ship, and manage anywhere from local, cloud, on-prem, or edge.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
A Zod-like implementation in PHP, inspired by Laravel's code standards.
real time face swap and one-click video deepfake with only a single image
AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.
Memory for AI Agents; SOTA in AI Agent Memory; Announcing OpenMemory MCP - local and secure memory management.
Simple, modular, and observable Go framework for backend applications.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Ultimate camera streaming application with support RTSP, RTMP, HTTP-FLV, WebRTC, MSE, HLS, MP4, MJPEG, HomeKit, FFmpeg, etc.
Helper tool for configuring routed IPTV on the UniFi Dream Machine (Pro)
A lightweight API resource for Laravel that helps you adhere to the JSON:API standard. Supports sparse fieldsets, compound documents, and more.
Provides a user-friendly, object-oriented API to build OpenAPI specifications using PHP
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
A diverse collection of WLED scenes
Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
OLED Stats Display Script For Raspberry Pi
A ground-up rebuild of the stock gridfinity bins in OpenSCAD