# External Context Feeds

> We create discrete feeds for external sources. Today one scores 100,000+ open-source science and technology entities in real time for your AI agents.

Canonical: https://www.adjective.us/ultimus/external-context

**External Sources.** A tear-away module of Ultimus.

- Builds a discrete feed per external source
- Scores new patterns in real time
- Feeds agents live, structured intelligence
- Helps optimize resource utilization

Agents need continuous awareness. A model trained last year does not know what shipped this week.

We create a discrete feed for each external source you care about. Each one is structured, scored, and live, and each one is served to your agents the way they read any other tool.

## The feed that runs today

Technical intelligence. It watches the open-source science and technology landscape, analyzing and scoring new patterns in real time, so your agents have something to consider. At over 100,000 scored entities, each score answers three questions.

- What is defensible.
- What is moving.
- What is risky.

The feed helps continuously optimize resource utilization.

## Any external source

Other external sources, such as OSV vulnerability data, become their own feeds. One source, one feed, one shape.

## Where it sits

This is the context of the outside. [Internal context feeds](/ultimus/environment-context) is the context of the inside. [Context management](/ultimus/context-management) sits between them.

## FAQ

**What is an external context feed?**

A discrete, structured feed we create for one external source, so agents can consider what is happening outside your walls, live.

**What feed runs today?**

Technical intelligence. It monitors the open-source science and technology landscape, analyzing and scoring real-time new patterns for agents to consider. At over 100,000 scored entities, it feeds your systems live, structured intelligence on what is defensible, what is moving, and what is risky.

**Which other sources can become feeds?**

Other external sources, such as OSV vulnerability data, become their own feeds. We create a discrete feed for each.

**Can agents call a feed directly?**

Yes. Feeds are served over MCP and API, so agents query them directly. The technical intelligence feed currently tracks 525 technical domains.