Integrates with Google Cloud Vertex AI for accessing AI models (DeepSeek, Kimi, MiniMax) in a multi-candidate agentic coding pipeline with planning, code generation, and quality gating.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Petamind MCP generate a React component for a user profile card with dark mode support"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This repository has been republished without the legacy Titan factory source.
The previously bundled synthetic UI dataset factory and related internal pipeline code are intentionally not included here.
This public repository is being reset to a minimal placeholder while the MCP/tooling split is redesigned.
Related MCP server: ai-architect
Prior public clones may still exist outside GitHub.
This repository no longer publishes the old factory code on the current public branch.
Codebase intelligence for agents: 152 structured artifacts across 21 programs, one call.
Coding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board.
Browser-backed QA with evidence and fix-ready reports for coding agents.
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
