django-ag-ui 0.1.1

Django ↔ Pydantic-AI ↔ AG-UI integration: async view, tool registry, audit logger.

django-ag-ui

Wire a Pydantic-AI agent into any Django project and speak the AG-UI protocol to a browser — a streaming agent endpoint, a typed tool registry, and the plumbing in between. No admin specifics; that lives in the downstream django-admin-agent, and the browser half is @artooi/ag-ui-web-component.

• Async AG-UI endpoint — DjangoAGUIView wraps Pydantic-AI's AGUIAdapter and returns a StreamingHttpResponse of AG-UI events (SSE). Conversation state rides in each request, so there's no cross-request session store and multi-worker deployments are safe by default.
• Typed tool registry — register plain callables with @tool; JSON Schema is derived from their signatures. destructive= / category= metadata surface as x-destructive / x-category extensions for client-side gating.
• Configurable agent — AgentConfig + the DJANGO_AG_UI settings cover the model, MODEL_SETTINGS, RETRIES, external TOOLSETS / CAPABILITIES, and an AGENT_FACTORY escape hatch for full control of construction.
• Audit boundary — an AuditLogger Protocol (Null / Logging shipped, pluggable by dotted path) records every server-side tool call.
• Opt-in conversation persistence — a ConversationStore Protocol with a no-op default, a session-backed store, and an abstract model-backed base.
• Reach external tools — compose any Pydantic-AI toolset, including an in-process drf-mcp bridge (the [drf-mcp] extra) so the agent can query DRF-exposed data.
• 100% test coverage, type-checked, Python 3.10–3.14, Django 4.2–6.0.

📖 Full documentation: https://artui.github.io/django-ag-ui/

pip install django-ag-ui
# or, with uv:
uv add django-ag-ui

ASGI required. The agent endpoint streams Server-Sent Events, which the sync WSGI worker can't serve — deploy under Daphne / Uvicorn.

---

Quick start

Register a read-only tool, mount the endpoint, and point a browser AG-UI client at it.

# tools.py
from django_ag_ui import ToolRegistry, tool

registry = ToolRegistry()


@tool(registry)
def count_active_users() -> int:
    """How many users are currently active."""
    from django.contrib.auth import get_user_model

    return get_user_model().objects.filter(is_active=True).count()

# urls.py
from django.urls import path  # noqa: F401

from django_ag_ui import DjangoAGUIView, get_urls

from .tools import registry

urlpatterns = [
    *get_urls(DjangoAGUIView(registry), prefix="agent/"),
]

# settings.py
DJANGO_AG_UI = {
    "MODEL": "anthropic:claude-sonnet-4.6",   # any Pydantic-AI model string
    # "MODEL_SETTINGS": {"temperature": 0.2},
    # "AUDIT_LOGGER": "django_ag_ui.LoggingAuditLogger",
    # "CONVERSATION_STORE": "django_ag_ui.DjangoSessionConversationStore",
}

POSTing an AG-UI RunAgentInput to /agent/ now streams the agent's run. Frontend-declared tools in the request are merged into the agent's catalog automatically; server-side tools run in-process. See the docs for the full settings reference, the persistence stores, and the drf-mcp bridge.

License

MIT — see LICENSE.