#694 · Primary category: AI Agents & Automation
agent-plugins-spec
Agent Plugins Specification v1.0.0 — A minimal standard for packaging agent extensions into distributable plugins
Project last updated:08/19/26
GitHub Stars
1.2K
Forks
63
Contributors
2
License
Other
Why we included this project
Teams building agent skills or MCP servers who want those components to travel between different agent clients, rather than living inside a single product, will find a concrete answer here. The project defines a minimal, vendor-neutral package format: a plugin directory with a small manifest plus skill or MCP configuration files, and a conforming client loads an extension just by reading the manifest. It is a specification, not a runtime, so its value is as a contract to design against when you are authoring distributable extensions or building a client that should consume them. The quick-start example takes minutes to grasp, and the versioned spec plus JSON schemas give implementers something concrete to validate against. If you are deciding how to package agent capabilities for reuse across tools, this is a short, readable baseline to start from.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.