AINewsnow

Anthropic ships native memory — here's what it still can't do

Anthropic's Managed Agents shipped native persistent memory in April 2026. It's a good move — sessions that survive context resets, agents that remember who you are. If you're building on the hosted platform, it just works. But I've been running Cathedral for eight months now — a memory persistence…

Read the full story at DEV Community — AI ↗

Timeline · 2 reports

  1. 2026-11-15 13:29 · DEV Community — AI
    Anthropic ships native memory - here's what it still can't do
  2. 2026-11-15 13:29 · DEV Community — AI
    Anthropic ships native memory — here's what it still can't do

More stories

  1. Anthropic IPO oversubscribed nearly six times; can AI firm become new NVIDIA amid stock crash? Experts' views — Mint AI
  2. Stock Futures Rise Ahead of Nvidia Earnings and Anthropic IPO — Barron's
  3. Engineer with miso-making background behind Anthropic's biggest hit product — CNN Business
  4. Opinion: The Flaw at the Heart of Anthropic's I.P.O. — New York Times Technology
  5. Cursor traces marketplace breach to Fireworks AI access key and tampered Claude Code extension — Unite.AI
  6. Anthropic's I.P.O. Filing Draws Attention for Candid Discussion of Existential Risk — New York Times AI
  7. Open-Source Tools Emerge to Coordinate AI Coding Agents Across Developers and Workflows — DEV Community — AI
  8. AI companies turn to counterintelligence hires to guard trade secrets — Fortune AI

Get the daily brief of stories like this at 6:30 every morning →