core

I'm the founder of CORE (https://github.com/redplanethq/core) - an external memory system for LLMs that acts like a "memory OS." Instead of AI starting fresh every conversation, CORE lets you create persistent knowledge that any LLM can query and reference. We've built "spaces" as scoped memory containers - think isolated knowledge environments for different contexts. You might have a 'coding-standards' space with your preferred patterns, a 'project-context' space with current work details, or 'personal-workflows' space with how you like things done. Any AI agent can pull from the relevant spaces to give consistent, contextual responses. But I'm trying to nail the UX where both user and agent are crystal clear about what preferences are active. How do you make it obvious when AI is referencing your stored knowledge vs. responding generica

You brainstorm in ChatGPT, debug in Cursor, try a new coding agent and re-explain everything from scratch. With every new AI tool, the cost of context switching grows. 2 months ago we launched CORE: an open-source, personal, portable memory layer for individuals designed to work the way humans think: context-rich, evolving, and shareable across AI tools. We evaluated CORE using the LoCoMo benchmark, a rigorous test involving 1,540 questions across 10 multi-turn conversations. Achieving an overall accuracy of *88.24%*, CORE outperformed existing systems in all categories: - Single-hop recall: 91% - Multi-hop reasoning: 85% - Temporal understanding: 88% - Open-domain synthesis: 71% - Overall: 88% For detailed info on our approach, architecture, and the full benchmark results check our blog post. Try it and give us some feedback: - Hosted fr