Tag: #machine-learning
38 packages âĸ â 305,989 total stars
Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Ultralytics YOLO đ for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
FinGPT: Open-Source Financial Large Language Models! Revolutionize đĨ We release the trained model on HuggingFace.
AI + Data, online. https://vespa.ai
A portable accelerated SQL query, search, and LLM-inference engine, written in Rust, for data-grounded AI apps and agents.
Curated list of the best truly open-source AI projects, models, tools, and infrastructure.
High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all f
A community-driven collection of RAG (Retrieval-Augmented Generation) frameworks, projects, and resources. Contribute and explore the evolving RAG ecosystem.
đ° PromptLayer - Maintain a log of your prompts and OpenAI API requests. Track, debug, and replay old completions.
Single-file memory layer for AI agents, sub mili-second RAG on Apple Silicon. Metal Optimized On-Device. No Server. No API. One File. Pure Swift
SDK libraries for Modal
⨠A curated list of awesome community resources, integrations, and examples of Redis in the AI ecosystem.
Your AI assistant that never forgets and runs 100% privately on your computer. Leave it on 24/7 - it learns your preferences, helps with code, manages your health goals, searches the web, and connects
Pure C ONNX runtime with zero dependancies for embedded devices
A framework for fine-tuning retrieval-augmented generation (RAG) systems.
Recipes and resources for building, deploying, and fine-tuning generative AI with Fireworks.
A comprehensive evaluation framework for AI agents and LLM applications.
OasisDB: A minimal and lightweight vector database
Claude Code skills, architectural principles, and alternative approaches for AI-assisted development
đŦ AI-powered YouTube Shorts automation tool using LLMs, real-time search, and text-to-speech. Create engaging short-form videos with automated research, voiceovers, and subtitles.
Control robots and physical hardware with natural language through Strands Agents.
A type-safe, lightweight, modern, and performant binding Java binding of Microsoft's ONNX Runtime
Paper-first SPY options validation platform with broker-backed scorecards, hard risk gates, paired-trade accounting, and live dashboards.
Local First AI SEO Software on Nix, FastHTML & HTMX
đ Enhance your academic writing with tailored AI prompt templates and practical agent skills to boost efficiency and reduce repetitive tasks.
AI-agent-friendly PyTorch research pipeline â one YAML config drives preflight, training, Optuna HPO, and real-time TUI monitoring
GEON: Structure-first decoding via equivalence classes and field closure
đ¤ Enhance chatbot accuracy with a self-correcting RAG system that ingests documents, retrieves data, and evaluates responses in real-time.
đ§ Orchestrate complex software projects with Claude Code's specialized agents for streamlined management and mandatory human oversight.
đ Learn from diverse sources with OmniLearnAI, an intelligent platform that combines documents, videos, and more, all with reliable citations.
Control autonomous AI agents by enforcing behavior rules to prevent unauthorized actions, improve focus, and boost execution efficiency.
Automate binary analysis by coordinating LLM agents with Ghidra, enabling scalable and precise reverse engineering workflows.
đ Enable local LLMs with real-time Google search, live feeds, OCR, and video insights using noapi-google-search-mcp server tools.
đ Run Python on Kaggle's free GPUs directly from your terminal without the need for a browser, streamlining your data science workflow.
A modular deep learning framework for training and evaluating image classification models on datasets like CIFAR-10 and MNIST. Supports configurable CNN architectures, automated training, and performa
No description