Enterprise AI Agent Platform
An enterprise AI agent platform on LangGraph and LangChain separating a governance control plane, covering auth, project management and audit, from an agent runtime handling graph orchestration, model assembly, tools, MCP and skills.
This project is a platform base for building enterprise AI agent applications, splitting a governance control plane from an agent runtime execution layer. The control plane covers authentication, project management, auditing and catalog management; the runtime layer covers agent graph orchestration, model assembly, and Tools, MCP and Skills integration with fast debugging.
The default checkout ships a demonstration set of five services end to end, including a Testcase Agent shown in a walkthrough video, and a platform-web frontend that is the current entry point for further development. It is aimed at teams that want to build on a mainstream agent technology stack, validate LangGraph runtime behaviour, or bring AI-assisted development into their own engineering process, and it documents its development rules and task-grading standard in a project AGENTS.md file.
It is built with LangGraph and LangChain in Python, and is described as suited for teams doing secondary development on top of it rather than as a finished product.