Pipeline and Data Version

• goml - line Machine Learning in Go (and so much more).
• golearn
• gonum
• gorgonia
• goro - level Machine Learning Library for Go.
• goga
• hep - hep.org/x/hep packages and tools.
• hector
• sklearn
• tokenizer
• spago - contained Machine Learning and Natural Language Processing library in Go.

Pipeline and Data Version

• go-neural
• go-deep
• olivia
• gomid
• neurgo
• gonn
• go-perceptron-go
• gobrain
• gosom - organizing maps in Go.

Pipeline and Data Version

• gosl
• sparse

Pipeline and Data Version

• godist

Pipeline and Data Version

• regression
• ridge

Pipeline and Data Version

• bayesian
• multibayes

Pipeline and Data Version

• too
• gorse
• regommend

Pipeline and Data Version

• eaopt
• evo

Pipeline and Data Version

• gogl

Pipeline and Data Version

• kmeans - means clustering algorithm implementation written in Go.
• gokmeans - means algorithm implemented in Go (golang).

Pipeline and Data Version

• anomalyzer
• goanomaly
• morgoth

Pipeline and Data Version

• gota
• dataframe-go - learning, and data manipulation/exploration.
• qframe

Pipeline and Data Version

• lime
• Machine-Learning-With-Go
• GO语言机器学习实战

DevTools

• go-attention
• swarmgo - sdk-go) is a Go package that allows you to create AI agents capable of interacting, coordinating, and executing tasks.
• orra - dev/orra project offers resilience for AI agent workflows.
• core - shot workflows, building autonomous agents, and working with LLM providers.
• gollm
• langchaingo - based programs in Go.
• gpt4all-bindings - language interfaces to easily integrate and interact with GPT4All's local LLMs, simplifying model loading and inference for developers.
• go-openai - 3, GPT-4, DALL·E, Whisper API wrapper for Go.
• llama.go
• eino
• fabric - source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
• genkit - powered apps with familiar code-centric patterns. Genkit makes it easy to develop, integrate, and test AI features with observability and evaluations. Genkit works with various models and platforms.
• ollama - R1, Phi-4, Gemma 2, and other large language models.

GPT

• gpt-go

SDKs

• go-anthropic
• deepseek-go - 1, Chat V3, and Coder. Also supports external providers like Azure, OpenRouter and Local Ollama.
• openai-go
• generative-ai-go
• anthropic-sdk-go - first language model APIs via Go.

ChatGPT Apps

• feishu-openai - 4 + GPT-4V + DALL·E-3 + Whisper) delivers an extraordinary work experience.
• chatgpt-telegram

Pipeline and Data Version

• pachyderm - Centric Pipelines and Data Versioning.

Vector Database

• milvus - performance, cloud-native vector database built for scalable vector ANN search.
• weaviate - source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.
• tidb - the open-source, cloud-native, distributed SQL database designed for modern applications.

Pipeline and Data Version

• Hands-on Reinforcement Learning
• OSS Insight - ->

Multi-modal

• gateway - Server for your Databases optimized for LLMs and AI-Agents.
• mcp-go
• mcp-golang

Code

• multi-swe-bench - SWE-bench project, developed by ByteDance's Doubao team, is the first open-source multilingual dataset for evaluating and enhancing large language models' ability to automatically debug code, covering 7 major programming languages (e.g., Java, C++, JavaScript) with real-world GitHub issues to benchmark "full-stack engineering" capabilities.
• BigCodeBench
• Code4Bench
• CRUXEval
• HumanEval
• MBPP - sourced Python programming problems, designed to be solvable by entry level programmers, covering programming fundamentals, standard library functionality, and so on.
• MultiPL-E - programming language benchmark for LLMs.
• SWE-bench - bench is a benchmark suite designed to evaluate the capabilities of large language models (LLMs) in solving real-world software engineering tasks, focusing on actual software bug-fixing challenges extracted from open-source projects.
• AIDER - related tasks, such as code writing and editing.
• LiveCodeBench
• BFCL - calling capability of different LLMs.

English

• ARC-AGI
• GPQA - Level Google-Proof Q&A Benchmark.
• ARC-Challenge
• BBH - Bench Tasks and Whether Chain-of-Thought Can Solve Them.
• HelloSwag
• IFEval - following capabilities of large language models by incorporating 25 verifiable instruction types (e.g., format constraints, keyword inclusion) and applying dual strict-loose metrics for automated, objective assessment of model compliance.
• MMLU-CF - free Multi-task Language Understanding Benchmark.
• MMLU-Pro - Task Language Understanding Benchmark.
• PIQA
• WinoGrande
• BIG-bench
• MMLU
• LiveBench - Free LLM Benchmark.

Math

• Omni-MATH - MATH is a comprehensive and challenging benchmark specifically designed to assess LLMs' mathematical reasoning at the Olympiad level.
• grade-school-math - step reasoning capabilities in language models, revealing that even large transformers struggle with these conceptually simple yet procedurally complex tasks.
• MATH - solving capabilities, offering dataset loaders, evaluation code, and pre-training data.
• MathVista
• TAU-bench - source benchmark suite designed to evaluate the performance of large language models (LLMs) on complex reasoning tasks across multiple domains.
• AIME

Chinese

• C-Eval
• CMMLU
• C-SimpleQA

Tool Use

• BFCL
• T-Eval - Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step.
• WildBench

Open ended

• Arena-Hard - Hard-Auto: An automatic LLM benchmark.

False refusal

• Xstest

Multi-modal

• geneval - focused framework for evaluating text-to-image alignment.
• LongVideoBench
• MLVU - task Long Video Understanding Benchmark.
• perception_test
• TempCompass
• Video-MME - MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.
• VBench - source project aiming to build a comprehensive evaluation benchmark for video generation models.
• DPG-Bench

• ADeLe
• SWELancer - Lancer-Benchmark** is designed to evaluate the capabilities of frontier LLMs in solving real-world freelance software engineering tasks, exploring their potential to generate economic value through complex software development scenarios.

Pipeline and Data Version

• MTEB - source benchmarking framework for evaluating and comparing text embedding models across 8 tasks (e.g., classification, retrieval, clustering) using 58 datasets in 112 languages, providing standardized performance metrics for model selection.
• BRIGHT - intensive retrieval, featuring 12 diverse datasets (math, code, biology, etc.) to evaluate retrieval models across complex, context-rich queries requiring logical inference.

Pipeline and Data Version

• CloudForest - threaded decision tree ensembles (Random Forest, Gradient Boosting, etc.) designed for high-dimensional heterogeneous data with missing values, emphasizing speed and robustness for real-world machine learning tasks.