Andrew Ng memo argues agent memory needs graphs, not bigger context windows
solyarisoftware · x · 2026-07-27
Andrew Ng’s new 15-page memo lays out a 4-step shift from loops to graphs for agent memory.
- The core argument: bigger context windows do not solve memory; they only delay forgetting until the next session.
- Instead of RAG over static documents, agents need a temporal knowledge graph that merges chat history and structured business data into one queryable layer.
- The key design choice is bi-temporal data: each fact keeps both the time it happened and the time the system learned it, so nothing is overwritten.
- Contradictions are invalidated, not deleted, which preserves answers like “who owned this in April” months later.
- The post also points to the paper’s benchmark results, including a claim that the system beats MemGPT on Deep Memory Retrieval.
The attached paper image shows the title “Zep: A Temporal Knowledge Graph Architecture for Agent Memory”, reinforcing that this is a concrete memory-stack proposal, not a high-level concept post.
Related event: Andrew Ng Advocates Graph-Based Memory for AI Agents(2 posts)→
More from coding & agent
- Vibe coding should be taught to sales and marketing teams, not PMs or designers — yangyi · 2026-07-27
- Grok Build and Unity CLI/MCP push an AI game from scaffold to polished demo — Daniel_Farinax · 2026-07-27
- opencode v1.18.7 fixes macOS fullscreen inset and project picker scrolling — opencode-agent[bot] · 2026-07-27
- OpenSpace targets a skill management layer for AI agents, not just more skills — solyarisoftware · 2026-07-27
- Can Chrome’s installed LLM drive a customer chat and call MCP tools? — DashinTheFields · 2026-07-27
- An unused gaming PC becomes a remote Claude Code workspace — rchardkovacs · 2026-07-27