Open Source Machine Learning Projects
Machine learning is a field of computing in which systems learn patterns from data to make predictions, classify information, generate content, or guide decisions. It helps address tasks that are difficult to solve with fixed rules, such as recognizing speech, detecting unusual activity, and forecasting demand. Methods range from statistical models trained on structured data to neural networks that work with text, images, audio, and other complex inputs.
Open source tools in this area include libraries for building and training models, datasets, experiment-tracking systems, evaluation utilities, and software for deploying inference. When choosing a tool, consider its license, documentation, maintenance activity, hardware and data requirements, and compatibility with your existing workflow. These resources are useful to learners, researchers, developers, and organizations building or evaluating data-driven applications.
191 repositories · updated October 4, 2026
verl-omni: Train Multimodal Generative Models with RL
VeRL-Omni is a Python framework for reinforcement-learning post-training of diffusion, unified multimodal, and omni-modality models. It builds on verl and targets teams that need distributed training, multimodal rollouts, and configurable reward workflows.
uni-agent: Train Long-Horizon Agents at Scale
Uni-Agent is a Python framework for running and training long-horizon agents through a shared interaction stack. It helps agent developers connect harnesses, tasks, tools, and sandboxes for scalable inference, evaluation, and reinforcement learning.
benchmark-radar: Discover AI Benchmarks and Track Evaluation Scores
Benchmark Radar gathers AI benchmark records and evaluation evidence from public sources in a searchable catalog. Use it to discover benchmarks, inspect reported scores and citations, and follow new findings through its dashboard or offline CLI.
shimmy: Serve Local GGUF Models with an OpenAI-Compatible API
Shimmy is a Rust inference server that runs GGUF language models locally and exposes an OpenAI-compatible API. It suits developers who want a lightweight alternative for connecting existing tools to local models without Python or llama.cpp.
AutoResearch: Turn Research Ideas into Reviewable Evidence
AutoResearch is a Python agent workflow for developing AI and machine learning research ideas into experiments and reviewable evidence. It suits researchers who want a traceable, resumable process and can configure model services and experiment resources.
AREX-Skill: Give Coding Agents Reusable ML Workflows
AREX-Skill is a library of executable, agent-readable workflows distilled from machine-learning repositories and research. Use it to help coding agents run, validate, and recover ML tasks with less unguided trial and error.
Awesome-Self-Evolving-Agents: Explore Research on Evolving Agents
A curated research index and survey companion covering self-evolving AI agents. It organizes papers, benchmarks, libraries, and applications for researchers and practitioners exploring how agents improve through model, environment, and combined evolution.
Curie: Automate Scientific Experiments with AI Agents
Curie is a Python framework that uses AI agents to plan, run, analyze, and report scientific experiments. It is aimed at researchers and ML practitioners who want reproducible experimentation across their own datasets and code.
awesome-automated-ai: Find Tools for Automated AI and ML
A curated directory of tools spanning AutoML, LLM fine-tuning, prompt optimization, AI agents, evaluation, and MLOps. Use it to survey options by category and follow links to projects that fit your workflow.
envharness: Adapt Environments for Agent Learning
EnvHarness wraps frozen interactive environments with composable layers that can target an AI agent’s weaknesses without changing benchmark code or grading. It is for researchers building and evaluating agent-training workflows across different environments.
ds4: Run DeepSeek and Other LLMs Locally
ds4, also called DwarfStar, is a native inference engine for selected open-weight language models on Apple Metal, NVIDIA CUDA, and AMD ROCm. It suits users with capable local hardware who want model-specific inference, serving, or coding-agent workflows.
Awesome-Dynamic-Agent-Skills: Survey Evolving Agent Skills
A curated reading list and taxonomy for research on dynamic skill libraries in LLM agents. Use it to compare skill formats, lifecycle stages, update operators, verification approaches, and safety research.