Suggestion: Add an AGENTS.md file
Claude Code, GitHub Copilot, Cursor, and Gemini CLI now read an AGENTS.md file at the repo root to understand how to contribute. It's purpose-built for AI agents, similar to how CONTRIBUTING.md is for humans.
Semantic Kernel is a multi-language AI orchestration SDK — an AGENTS.md could help AI assistants navigate the codebase by covering:
- Which language SDK to look in for a given concept (Python vs C# vs Java)
- How to run the test suites in each language
- Conventions for adding new connectors or memory implementations
- Which files/patterns to study before modifying the planner or kernel
- Things to avoid (e.g., breaking cross-language API parity)
Why now
With AI-assisted development becoming the norm, many contributors to projects like this one use Claude Code, Copilot, or Cursor. A well-written AGENTS.md reduces incorrect assumptions and improves the quality of AI-generated PRs.
Projects like LangChain, Pydantic, and the OpenAI SDK have already adopted this convention.
Happy to contribute a draft if that would help.
Suggestion: Add an AGENTS.md file
Claude Code, GitHub Copilot, Cursor, and Gemini CLI now read an
AGENTS.mdfile at the repo root to understand how to contribute. It's purpose-built for AI agents, similar to howCONTRIBUTING.mdis for humans.Semantic Kernel is a multi-language AI orchestration SDK — an
AGENTS.mdcould help AI assistants navigate the codebase by covering:Why now
With AI-assisted development becoming the norm, many contributors to projects like this one use Claude Code, Copilot, or Cursor. A well-written
AGENTS.mdreduces incorrect assumptions and improves the quality of AI-generated PRs.Projects like LangChain, Pydantic, and the OpenAI SDK have already adopted this convention.
Happy to contribute a draft if that would help.