gdabas

gdabas's Stars

• openai/whisper

  Robust Speech Recognition via Large-Scale Weak Supervision

  Language:Python79k63609.5k

• hacksider/Deep-Live-Cam

  real time face swap and one-click video deepfake with only a single image

  Language:Python48.4k3026897.1k

• microsoft/markitdown

  Python tool for converting files and office documents to Markdown.

  Language:Python41.5k1392112k

• unslothai/unsloth

  Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

  Language:Python35.9k2091.7k2.8k

• mem0ai/mem0

  The Memory layer for AI Agents

  Language:Python26.8k1437822.5k

• modelcontextprotocol/servers

  Model Context Protocol Servers

  Language:JavaScript26k1713112.7k

• VikParuchuri/marker

  Convert PDF to markdown + JSON quickly with high accuracy

  Language:Python23.4k954161.4k

• stanfordnlp/dspy

  DSPy: The framework for programming—not prompting—language models

  Language:Python22.7k1521k1.7k

• agno-agi/agno

  Agno is a lightweight library for building Multimodal Agents. It exposes LLMs as a unified API and gives them superpowers like memory, knowledge, tools and reasoning.

  Language:Python22.4k1556602.9k

• black-forest-labs/flux

  Official inference repo for FLUX.1 models

  Language:Python21k1752041.5k

• CopilotKit/CopilotKit

  React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic last-mile 🪁

  Language:TypeScript17.7k1092902.5k

• OpenTalker/SadTalker

  [CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

  Language:Python12.5k1548292.3k

• instantX-research/InstantID

  InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

  Language:Python11.5k126236833

• anthropics/anthropic-quickstarts

  A collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API

  Language:TypeScript8.4k781491.4k

• KoljaB/RealtimeSTT

  A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

  Language:Python6.5k60137522

• QwenLM/Qwen2.5-Coder

  Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

  Language:Python4.7k43159370

• katanaml/sparrow

  Data processing with ML, LLM and Vision LLM

  Language:Python4.4k5575445

• Picovoice/porcupine

  On-device wake word detection powered by deep learning

  Language:Python4k65567514

• VectorSpaceLab/OmniGen

  OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

  Language:Jupyter Notebook3.8k85165330

• NirDiamant/Prompt_Engineering

  This repository offers a comprehensive collection of tutorials and implementations for Prompt Engineering techniques, ranging from fundamental concepts to advanced strategies. It serves as an essential resource for mastering the art of effectively communicating with and leveraging large language models in AI applications.

  Language:Jupyter Notebook3.6k412424

• NovaSky-AI/SkyThought

  Sky-T1: Train your own O1 preview model within $450

  Language:Python3.2k4245320

• langchain-ai/langgraph-studio

  Desktop app for prototyping and debugging LangGraph applications locally.

  2.7k33220167

• NVIDIA/nv-ingest

  NVIDIA Ingest is an early access set of microservices for parsing hundreds of thousands of complex, messy unstructured PDFs and other enterprise documents into metadata and text to embed into retrieval systems.

  Language:Python2.6k29150227

• svpino/alloy-voice-assistant

  Language:Python9631510333

• THUDM/LongCite

  LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

  Language:Python481121634

• hwchase17/langgraph-engineer

  Language:Python2765043

• docker/mcp-servers

  Model Context Protocol Servers

  Language:JavaScript1543815

• jbarnes850/deepseek-r1-finetune

  A step by step guide to fine-tuning the DeepSeek R1 Distilled models on Apple Silicon machines.

  Language:Python52337

• ssc-dsai/canchat-v2

  User-friendly WebUI for LLMs (Formerly Ollama WebUI)

  Language:JavaScript9207

• gdabas/PowerPrompter

  Language:TypeScript1100