Tag

LightRAG is an open-source framework designed for simple and fast Retrieval-Augmented Generation (RAG), integrating knowledge graphs, vector search, and efficient LLM-based processing to enhance question-answering over large document collections.

OpenCode is the open source AI coding agent built for the terminal. It features built-in agents (build, plan, general), LSP support, multi-provider LLM compatibility (75+ including Claude, GPT, Gemini, local), native TUI, multi-session, share links, and privacy-first design. No account needed, 35k+ stars.

Claude Quickstarts is a collection of projects by Anthropic to help developers quickly build deployable applications using the Claude API. It includes quickstarts for a customer support agent, financial data analyst, computer use demo, and autonomous coding agent, demonstrating Claude's capabilities in natural language processing, data analysis, computer control, and automated coding.

AI Toolkit is an all-in-one training suite for finetuning diffusion models, supporting image and video models on consumer-grade hardware. It offers GUI and CLI interfaces, making it user-friendly yet feature-rich, with capabilities for dataset handling, LoRA/LoKr training, layer-specific training, and integrations with platforms like RunPod and Modal. It supports models like FLUX.1 and SDXL, requiring an NVIDIA GPU with at least 24GB VRAM.

NumPy is the fundamental package for scientific computing in Python. It provides a powerful N-dimensional array object, broadcasting operations, linear algebra, FFT, random number capabilities, and integration with C/C++/Fortran, and serves as a core building block for many AI and scientific libraries.

Provides APIs to build, learn, and run Bayesian and dynamic Bayesian networks, perform probabilistic inference, and compute interventional/counterfactual queries. Ships example notebooks, tutorials, and PyPI/conda packages. ([github.com](https://github.com/pgmpy/pgmpy))

High-performance, scalable gradient-boosted decision tree library for regression, classification, ranking and custom objectives. Multi-language bindings (Python, R, Java, Scala, C++), single-node, distributed and GPU training — widely used for tabular data and ML competitions.

Programmatically author, schedule, and monitor data workflows using Python-defined DAGs. Features modular executors, rich provider/operator ecosystem (Kubernetes, AWS, GCP), and built-in scheduling/monitoring for batch and ML pipelines.

Processes and indexes digital evidence for forensic analysis (disk images, files, timelines). Offers high-speed carving, OCR (Tesseract), NER, similar-document/image and face search, audio transcription and scriptable parsers — Java-based and extensible for investigators.

Provides readable Python implementations and animated demos of core robotics algorithms (localization, SLAM, mapping, path planning, control). Minimal dependencies and a companion online textbook make it a practical teaching/reference repository for students and researchers.

High-performance gradient-boosting decision-tree library for training and serving tabular ML models; uses histogram-based learning, leaf-wise tree growth and GOSS for faster training, with Python/R bindings, distributed and GPU support.

openpilot is an operating system for robotics developed by comma.ai. It upgrades the driver assistance system on over 300 supported cars, providing advanced features like lane centering, adaptive cruise control, and path planning.