Field Watch — Lab

Llama (Meta)

Last updated 21 October 2026

Why it matters

Meta publishes Llama weights that anyone can download and run under the Llama 4 Community License. Llama 4 Scout and Llama 4 Maverick were released on 5 April 2025; the model card lists a context length of 10 million tokens for Scout and 1 million for Maverick, and describes each as a static model trained on an offline dataset. The weights carry no memory between sessions: whatever an assistant built on Llama remembers is stored and governed by the application around it. Meta's open-source agent server, Llama Stack, is now named OGX; its repository describes an MIT-licensed, OpenAI-compatible API server with tool calling, MCP server integration and file search. It does not describe a memory feature.

Primary sources

Status

ActiveOpen-weight model family — memory lives in your application

Date observed: 2026-10-21

Last verified: 2026-10-21

How entries are chosen, categorized, and re-checked: How the map works.

Cite this page

Last updated: 2026-10-21

Maintained by: The Continuity Layer

How to cite: Cite the specific page and section (e.g., “The Continuity Layer, Llama (Meta)”), not the site as a general source. Attribute to The Continuity Layer.

Canonical URL: https://thecontinuitylayer.com/field-watch/meta-llama

Suggested citation: The Continuity Layer. “Llama (Meta).” https://thecontinuitylayer.com/field-watch/meta-llama (last updated 2026-10-21).

Continuity layer — this site’s working definition: A continuity layer is the part of an AI system that carries forward governed state across sessions, tools, and models: what is currently true, what changed, why it changed, and which evidence supports it. It sits above memory and retrieval, and below agent execution, turning stored history into usable, auditable continuity.