Short-term and long-term memory are the base layer of AI assistants
goyalshaliniuk · x · 2026-07-27
- Short-term memory is described as an agent’s working memory: current conversations, recent actions, immediate context, and temporary information.
- Long-term memory stores user preferences, historical conversations, project information, and persistent knowledge across interactions.
- The thread’s point is that long-term memory is what makes AI systems feel personalized, while short-term memory handles the active task at hand.
Related event: Shalini Goyal maps 10 memory systems for AI agents(12 posts)→
More from coding & agent
- theo builds his own visualizer for today's agent models, showing how cheap Luna really is — ivan_bezdomny · 2026-09-23
- Vite+ Hits RC: One Rust-Powered CLI to Replace Your Entire Web Toolchain — cnakazawa · 2026-09-23
- Tesla's in-car Grok agent books trips across Gmail, Calendar and Notion in one command — xiaohu · 2026-09-23
- Tesla's In-Car Grok Assistant Now Executes Cross-App Tasks in One Sentence — xiaohu · 2026-09-23
- Garry Tan says Capy lets him ship PRs much faster than Codex or Claude Code — garrytan · 2026-09-23
- DeskPilot: open-source native Python desktop client for local LLMs with MCP and sandboxed tools — poofph · 2026-09-23