GitHub-проекты

Modular pipelines for retrieval and generative AI applications.

Patterns for agents that make progress across multiple context windows and recover from failure.

Google зарелизил Agent2Agent (A2A) протокол для взаимодействия агентов.

A small SDK for tools, handoffs, guardrails, tracing, and agent orchestration.

Low-level orchestration for long-running, stateful agents.

A vendor-neutral specification for agent discovery, task delegation, streaming, asynchronous updates, and cross-platform communication.

Пару дней программировал с Claude Code - это приложение-агент для терминала, которое умеет не только просто писать код,

Risks and mitigations for developing and deploying generative AI applications.

How to select, structure, and manage the context available to long-running agents.

Code examples for structured outputs, tool use, retrieval, evals, and other LLM application patterns.

Меня часто иногда спрашивают про всякие курсы по тому, как писать промпты к LLMкам. Могу порекомендовать бесплатный мин

An introductory path through generative AI concepts and Google Cloud tooling.

Reinforcement Learning: пошаговый план изучения Reinforcement Learning (RL) лежит в основе многих ключевых достижений

Build neural networks and language models from first principles.

A paid program for agentic coding and building, testing, and shipping production AI systems.

Theory, intuition, and practical notebooks by Simon Prince.

A probability-grounded treatment by Christopher and Hugh Bishop.

Mathematical foundations by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.

A concise, technical introduction by Andriy Burkov.

LLMOps, fine-tuning, serving, and production workflows.

A visual and practical guide by Jay Alammar and Maarten Grootendorst.

The broad reference for classical AI, including search, reasoning, planning, learning, and robotics.

Discover open source deep learning code and pretrained models.

Train Machine Learning models on the fly to recognize your own images, sounds, & poses.

An opensource viewer for neural network, deep learning and machine learning models

Free, open-access search engine for robotics, ML, and AI research papers (arXiv, MDPI, IEEE OA).

An online tool to generate boilerplate machine learning code that uses scikit-learn.

Machine learning experiment tracking, dataset versioning, hyperparameter search, visualization, and collaboration

platform to manage the ML lifecycle, including experimentation, reproducibility and deployment. Framework and language agnostic, take a look at all the built-in integrations.

ML platform for tracking experiments, hyper-parameters, artifacts and more. It's deeply integrated with over 15+ deep learning frameworks and orchestration tools. Users can also use the platform to monitor their models in production.

Tool to log, analyze, compare and "optimize" experiments. It's cross-platform and framework independent, and provided integrated visualizers such as tensorboard.

MLReef is an end-to-end development platform using the power of git to give structure and deep collaboration possibilities to the ML development process.

Is an open source on-prem AI coding autonomous assistant that lives inside your repo, edits and tests files at SSD speed. Think Claude Code but with UI. plug in any LLM (OpenAI, Gemini, Ollama, etc.) and let it work for you.

Production AI plaftorm for deploying, managing, and observing any model at scale across any environment from cloud to edge. Let's go from python notebook to inferencing in minutes.

Browser-based visual editor for designing neural networks and automatically generating PyTorch and TensorFlow code.

Interactive visualizations explaining neural networks, backpropagation, attention mechanisms, and transformers.

A page of content on TensorFlow, including academic papers and links to related topics.

Creating statically typed dynamic neural networks from object-oriented & functional programming constructs.

Interactive and Reactive Data Science using Scala and Spark.

ScalaNLP is a suite of machine learning and numerical computing libraries.

and quanteda are the main packages for managing, analyzing, and visualizing textual data.

A data visualization package based on the grammar of graphics.

data.table provides a high-performance version of base R’s data.frame with syntax and feature enhancements for ease of use, convenience and programming speed.

medley: Blending regression models, using a greedy stepwise approach.

ipred - ipred: Improved Predictors.

CORElearn - CORElearn: Classification, regression, feature evaluation and ordinal evaluation.

Classification and Regression Training: Unified interface to ~150 ML algorithms in R.

Glean - A data management tool for humans. [Deprecated]