Another very cost-effective option is Ollama Cloud. In a month of use, I only hit the 5-hour limit once, when I ran 8 agents simultaneously for 2 hours.
It seems like any project that makes fun of Claude is bound to reach the top spot on Hacker News. Even if it’s just a project consisting of four lines of code.
When we give LLM access to the terminal, LLM doesn't need anything else. LLM already knows all the commands, and there's no need to waste context on MCP. When we tell it to use a new command, it can get `--help` as needed.
I also started working on a similar project, but I think that LLM should know and be able to keep internal statistics about players. In poker, the best hand does not always win. Often, you can win by using emotions/words. LLM should be given the ability to communicate, mislead, etc.