# Agent Frameworks

Highflame Shield provides first-class integrations for popular agent frameworks across Python and TypeScript. Each integration intercepts model calls and tool executions at the framework level without requiring changes to individual agents, tasks, or tool implementations.

### Available Integrations

| Framework            | Class                        | Python                               | TypeScript                   |
| -------------------- | ---------------------------- | ------------------------------------ | ---------------------------- |
| **LangGraph**        | `HighflameMiddleware`        | `pip install 'highflame[langgraph]'` | `npm install @highflame/sdk` |
| **CrewAI**           | `HighflameCrewHooks`         | `pip install 'highflame[crewai]'`    | `npm install @highflame/sdk` |
| **AWS Strands**      | `HighflameStrandsHooks`      | `pip install 'highflame[strands]'`   | `npm install @highflame/sdk` |
| **Azure AI Foundry** | `HighflameFoundryMiddleware` | `pip install 'highflame[foundry]'`   | `npm install @highflame/sdk` |

All integrations share the same behavior:

* Each intercepted point evaluates against your active Cedar policies
* On a policy violation with `mode="enforce"`, `BlockedError` is raised
* `mode="monitor"` and `mode="alert"` observe without blocking
* Session IDs are resolved automatically from framework context where possible

{% content-ref url="/pages/m1yOjNKWd0sYSyce9xBR" %}
[LangGraph](/api-reference/sdk/shield/integrations/langgraph.md)
{% endcontent-ref %}

{% content-ref url="/pages/PUIeQp3x8gfldUZZhv8S" %}
[CrewAI](/api-reference/sdk/shield/integrations/crewai.md)
{% endcontent-ref %}

{% content-ref url="/pages/KqXhYK72usBBfbim23H5" %}
[AWS Strands](/api-reference/sdk/shield/integrations/strands.md)
{% endcontent-ref %}

{% content-ref url="<https://github.com/highflame-ai/highflame-docs/blob/main/api-reference/sdk/shield/integrations/foundry.md>" %}
<https://github.com/highflame-ai/highflame-docs/blob/main/api-reference/sdk/shield/integrations/foundry.md>
{% endcontent-ref %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.highflame.ai/api-reference/sdk/shield/integrations.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.