His other projects like CodexBar and Oracle are great too. I love diving into his code to learn more about how those are built.
OpenClaw is something I don’t quite understand. I’m not sure what it can do that you can’t do right off the bat with Claude Code and other terminal agents. Long term memory is one, but to me that pollutes the context. Even if an LLM has 200K or 1M context, I always notice degradation after 100K. Putting in a heavy chunk for memory will make the agent worse at simple tasks.
One thing I did learn was that OpenClaw uses Pi under the hood. Pi is yet another terminal agent like ClaudeCode but it seems simple and lightweight. It’s actually the only agent I could get Gemini 3 Flash and Pro to consistently use tools with without going into loops.