GitHub - cpacker/MemGPT: Teaching LLMs memory management for unbounded context 📚🦙
Folks who are building their own personal assistants with AI:
How do you handle memory?
Does the AI save notes in tool calls?
How do you prevent context rot?
Do you feed the entire memory into every LLM call, or retrieve only the most relevant bits?
Matt Pocockx.comJust a moment...
datacamp.comGitHub - infiniflow/ragflow: RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
infiniflowgithub.com