Phuriwaj

Freewrite

A focused Saturday of AI tooling and stack research. The main thread was evaluating MiniMax M2.7 as the LLM backend for a new admin portal β€” stack decided as Mantine v9 + Next.js + M2.7 via OpenAI-compatible SDK. Also explored y-router as a cleaner alternative to the LiteLLM proxy issue for running non-Anthropic models in Claude Code. Quick utility questions filled in the gaps: killing dev server ports and using gstack’s post-coding workflow.

Big Things Today

  • Scaffold the Mantine + Next.js + MiniMax M2.7 admin portal starter project
  • Test y-router (https://cc.yovy.app) as alternative to LiteLLM proxy for CC-Autonomous

Conversations

AI Stack Research

Minimax 2.7 overview β€” Mantine + LLM Setup

Researched how to give Minimax M2.7 accurate awareness of Mantine v9 (post-training cutoff UI library). Three options: MCP server (@mantine/mcp-server), llms.txt URL, or prebuilt skills. Recommendation: MCP server + skills combo for full coverage. β†’ See reference/mantine-llm-setup

MUI vs Tailwind/shadcn comparison β€” MiniMax M2.7 API

Stack decision conversation: Mantine + Next.js + MiniMax M2.7 is confirmed as the admin portal stack. M2.7 API is OpenAI-compatible β€” just swap baseURL to https://api.minimax.io/v1. Together AI is a managed alternative. Recommended params: temp=1.0, top_p=0.95. Next step: scaffold starter project. β†’ See reference/minimax-m27-api | efforts/on/minimax-admin-portal

Claude Code Tooling

CC-Autonomous β€” y-router for OpenRouter models

Explored running Claude Code with non-Anthropic models via OpenRouter + y-router. y-router bridges Anthropic API format β†’ OpenAI format. Hosted version (https://cc.yovy.app) enables GitHub Actions with GLM-4.5, Gemini, etc. Key env vars: ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, blank ANTHROPIC_API_KEY. Warning: not reliable for production β€” tool calls may break with non-Anthropic providers. β†’ See reference/claude-code-openrouter-y-router | efforts/on/litellm-local-llm

Identifying the next command after coding β€” gstack workflow

Researched gstack (Garry Tan’s 23-tool Claude Code setup) for the post-coding phase. Standard sequence: /review β†’ /qa <url> β†’ /ship β†’ /land-and-deploy β†’ /canary. Sprint order: Think β†’ Plan β†’ Build β†’ Review β†’ Test β†’ Ship β†’ Reflect. β†’ See reference/gstack-post-coding-workflow

Dev Utilities

Kill process on port 3000

Quick reference: lsof -ti:3000 | xargs kill -9. Also: Next.js 15 moved turbopack from experimental.turbopack to top-level turbopack: true in next.config.ts. β†’ See reference/kill-process-by-port

Open Tasks Surfaced

  • Scaffold Mantine + Next.js + M2.7 admin portal starter project
  • Set up @mantine/mcp-server in Claude Desktop MCP config
  • Test y-router hosted version for CC-Autonomous GitHub Actions
  • Add /review β†’ /qa β†’ /ship gstack workflow to existing project

Insights Worth Developing