OpenJarvis is a research framework from Stanford’s Scaling Intelligence Lab for building personal AI agents that run locally by default. Unlike cloud-dependent agent frameworks, OpenJarvis only calls external APIs when truly necessary — keeping your data private and your workflows fast. The project is available at github.com/open-jarvis/OpenJarvis. Seven Built-in Agent Types OpenJarvis ships with seven
The Model Context Protocol (MCP) has become the standard way AI agents connect to external tools and data sources. The official MCP Servers repository on GitHub is where it all starts — a growing collection of reference implementations that demonstrate how to build MCP-compatible tools for any AI agent. Official Reference Servers The modelcontextprotocol GitHub
Nous Research has released Hermes Agent, an open-source AI agent that does something no other agent framework does well: it learns and improves from every interaction. With 70+ bundled skills across 15+ categories and a built-in learning loop, Hermes Agent creates new skills from experience and deepens its understanding of each user over time. How
Finding quality AI agent skills among thousands of options can be overwhelming. Thankfully, the community has built several excellent curated lists. Here are the top awesome agent skills repositories on GitHub worth bookmarking. VoltAgent/awesome-agent-skills — 500+ Verified Skills VoltAgent/awesome-agent-skills is the gold standard. Unlike bulk-generated repositories, this collection focuses on real-world agent skills created by
With over 280,000 GitHub stars, OpenClaw has become the most popular open-source project in history — and its skills ecosystem is a major reason why. The OpenClaw GitHub repository houses the complete framework for building, running, and deploying AI agents that integrate with any large language model including Claude, DeepSeek, and GPT models. What Makes