Only have 420 watched repos so no idea why it thinks i have 10k heh

But I am not where near my GitHub repo watch limit

Looks like Claude Code 2.0.36 is constantly allowing me to initially go over my 200K context quota before clamping down on the limit

For slow Kimi K2 Thinking model via Openrouter AI provider in Kilo Code - definitely slower experience than what Openrouter AI reported 17-26 tokens/second

Moonshot Kimi K2 Thinking via Openrouter AI provider in Kilo Code? at least 15x times slower than Claude Code Sonnet 4.5 task and it actually failed to complete the task!

My Debian 12 Docker based Microsoft Visual Studio Code dev container on macOS where these tools can party together in an isolated container - OpenAI Codex CLI, Gemini CLI, Claude Code, OpenCode CLI, Vercel CLI, Cloudflare Wrangler, AWS CLI 🤓

Added OpenCode CLI and Visual Studio Code extension to my Debian 12 Docker based VSC dev container so that all these tools can party together in an isolated container - OpenAI Codex CLI, Gemini CLI, Claude Code, Vercel CLI, Cloudflare Wrangler, AWS CLI 🤓

This is Claude Code + Openai Codex CLI + Gemini CLI in one Visual Studio Code multi-tab supported dev container with full visual IDE/MCP support 🤓 Best of both worlds CLI + GUI editor 😎

Looks like OpenAI's new gpt-5-codex-mini LLM model in Codex CLI has a 272K token context window