Took @VictorTaelin’s awesome experiments around compressing GPT prompts and built CompressGPT. A one-line change in your @langchain code => 70% token usage deduction!
Finally got around to publishing the hooks framework I've been using to run 40+ @claudeai sessions in parallel daily while maintaining excellent code quality! It's self-improving and opens about a PR a day with new rules for me. Some of my favorite use cases below!
.@superpower gives you a really cool “import from AI” onboarding experience… which does exactly nothing because the agent doesn’t have any tools to actually persist the data. smh another vacuous LLM product 😕
