The open-source benchmark for LLM memory decay. Measure how Naive, RAG, Chunked RAG, Cascading, and SummaryMemory degrade over 100 conversation turns. Ebbinghaus forgetting curves, 5-provider LLM eval, multi-seed CI. No API key needed.
Related
PengZhang64/circuit-framework: Circuit Framework — multi-agent LLM trading research system
Circuit Framework — multi-agent LLM trading research system
airupt/generative-ai-skill: Claude Code skill: generative AI engineering reference distilled from Microsoft's Generative AI for Beginners (MIT)
Claude Code skill: generative AI engineering reference distilled from Microsoft's Generative AI for Beginners (MIT)
Zeil6/lerobot-so101-imitation-learning: A hands-on reproduction of ACT and Diffusion Policy on the SO-101 robot with LeRobot, covering data collection, training, deployment, debugging, and experiment reflections.
A hands-on reproduction of ACT and Diffusion Policy on the SO-101 robot with LeRobot, covering data collection, training, deployment, debugging, and experiment reflections.