Open Source Artificial Intelligence Projects
Artificial intelligence (AI) refers to systems that perform tasks commonly associated with human intelligence, such as recognizing patterns, generating content, making predictions, and supporting decisions. AI technologies can help automate repetitive work, analyze large or complex datasets, and build interactive applications. They range from machine learning methods that learn from data to generative models that create text, images, audio, or code, as well as software that coordinates AI-driven workflows.
Open source AI tools include model libraries, training and inference frameworks, data-processing utilities, evaluation and monitoring systems, and agent-building components. When choosing a tool, consider its license, documentation, maintenance activity, hardware and software requirements, data handling, and compatibility with your existing systems. These tools can be useful to researchers, developers, organizations, and learners exploring AI or integrating it into applications, while the right choice depends on the intended task and available resources.
14 repositories · updated October 3, 2026
Awesome-Self-Improving-Agents: A Curated List for Agentic AI Self-Improvement
Awesome-Self-Improving-Agents is a comprehensive GitHub repository featuring a curated and continuously updated list of resources on self-improvement in foundation model-based agentic systems. It serves as a central hub for researchers and practitioners, offering papers, benchmarks, and various media. This resource is essential for anyone exploring the cutting edge of self-evolving AI agents.
Curie: Automated and Rigorous Scientific Experimentation with AI Agents
Curie is an innovative AI-agent framework designed for automating rigorous scientific experimentation. It streamlines the entire research lifecycle, from hypothesis formulation to result interpretation, ensuring precision, reliability, and reproducibility. This empowers scientists to accelerate their research processes significantly.
Product-Manager-Skills: AI-Powered Framework for Product Management Excellence
Product-Manager-Skills is a comprehensive GitHub repository offering a framework of 77 battle-tested product management skills. Designed for AI agents like Claude, Codex, and ChatGPT, it helps product managers and their AI counterparts achieve professional-level work. This resource aims to provide both functional tools and pedagogic insights into effective product management practices.
Agent Skills: A Standardized Way to Give AI Agents New Capabilities
Agent Skills provides a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows. It allows packaging procedural knowledge and context into portable, version-controlled folders that agents load on demand. This enables agents to gain domain expertise, follow repeatable workflows, and reuse skills across various compatible AI tools.
OpenHands: AI-Driven Development with Agent Canvas
OpenHands Agent Canvas is a self-hosted developer control center designed for coding agents and automations. It allows users to run various AI agents, including OpenHands, Claude Code, and Codex, across local, remote, and cloud backends. This powerful platform helps automate everyday development tasks, turning coding agents into an always-on engineering team.
Awesome AI Agents 2026: The Ultimate List of AI Tools and Frameworks
This repository, `awesome-ai-agents-2026`, is a comprehensive and frequently updated collection of over 340 AI agents, frameworks, and tools across more than 20 categories. It serves as an essential resource for developers and researchers looking to explore the rapidly evolving landscape of artificial intelligence in 2026, covering everything from coding agents to creative AI and governance.
AsterMind-ELM: Modular Extreme Learning Machine for On-Device ML in JS/TS
AsterMind-ELM is a JavaScript/TypeScript library that modernizes Extreme Learning Machines (ELMs) for instant, on-device machine learning in web applications. It offers advanced features like Kernel ELMs, Online ELM, and DeepELM, enabling fast, private, and interpretable AI directly in the browser. This framework allows for building decentralized, self-training ML systems without relying on GPUs or servers.
claude-mem: Persistent Context Across Sessions for AI Agents
claude-mem is an innovative GitHub repository designed to provide persistent context across sessions for various AI agents. It intelligently captures agent activities, compresses them using AI, and injects relevant information into future interactions. This powerful tool supports a wide range of AI platforms, including Claude Code, OpenClaw, Gemini, and Copilot.
LLMSanitize: An Open-Source Library for Contamination Detection in NLP and LLM Datasets
LLMSanitize is an open-source Python library designed for detecting contamination in NLP datasets and Large Language Models (LLMs). It offers a comprehensive suite of methods, ranging from string matching to model likelihood and embedding similarity, to ensure data integrity. This tool is crucial for researchers and developers working with LLMs to maintain the reliability of their models and evaluations.
fastrtc: Build Real-Time Audio and Video Apps in Python
FastRTC turns Python functions into real-time audio and video streams over WebRTC or WebSockets. It suits developers building voice, video, and AI interaction features who want stream handling and optional Gradio or FastAPI integration.
Memary: The Open Source Memory Layer for Autonomous Agents
Memary is an innovative open-source memory layer designed to enhance autonomous agents by emulating human memory. It integrates knowledge graphs and memory modules to provide agents with advanced capabilities for reasoning and learning. This project aims to make agents more intelligent and capable of self-improvement.
scikit-learn: The Essential Python Library for Machine Learning
scikit-learn is a widely-used open-source Python library for machine learning, built upon SciPy. It provides a comprehensive suite of tools for data mining and data analysis, making it an indispensable resource for developers and data scientists. With its extensive algorithms and user-friendly interface, scikit-learn simplifies complex machine learning tasks.