This release is a pre-release and may not be stable for production use.
Agent Framework AG-UI Integration
AG-UI protocol integration for Agent Framework, enabling seamless integration with AG-UI's web interface and streaming protocol.
Installation
pip install agent-framework-ag-ui
Quick Start
Server (Host an AI Agent)
from fastapi import FastAPI
from agent_framework import ChatAgent
from agent_framework.azure import AzureOpenAIChatClient
from agent_framework.ag_ui import add_agent_framework_fastapi_endpoint
# Create your agent
agent = ChatAgent(
name="my_agent",
instructions="You are a helpful assistant.",
chat_client=AzureOpenAIChatClient(
endpoint="https://your-resource.openai.azure.com/",
deployment_name="gpt-4o-mini",
api_key="your-api-key",
),
)
# Create FastAPI app and add AG-UI endpoint
app = FastAPI()
add_agent_framework_fastapi_endpoint(app, agent, "/")
# Run with: uvicorn main:app --reload
Client (Connect to an AG-UI Server)
import asyncio
from agent_framework import TextContent
from agent_framework.ag_ui import AGUIChatClient
async def main():
async with AGUIChatClient(endpoint="http://localhost:8000/") as client:
# Stream responses
async for update in client.get_streaming_response("Hello!"):
for content in update.contents:
if isinstance(content, TextContent):
print(content.text, end="", flush=True)
print()
asyncio.run(main())
The AGUIChatClient supports:
- Streaming and non-streaming responses
- Hybrid tool execution (client-side + server-side tools)
- Automatic thread management for conversation continuity
- Integration with
ChatAgentfor client-side history management
Documentation
- Getting Started Tutorial - Step-by-step guide to building AG-UI servers and clients
- Server setup with FastAPI
- Client examples using
AGUIChatClient - Hybrid tool execution (client-side + server-side)
- Thread management and conversation continuity
- Examples - Complete examples for AG-UI features
Features
This integration supports all 7 AG-UI features:
- Agentic Chat: Basic streaming chat with tool calling support
- Backend Tool Rendering: Tools executed on backend with results streamed to client
- Human in the Loop: Function approval requests for user confirmation before tool execution
- Agentic Generative UI: Async tools for long-running operations with progress updates
- Tool-based Generative UI: Custom UI components rendered on frontend based on tool calls
- Shared State: Bidirectional state sync between client and server
- Predictive State Updates: Stream tool arguments as optimistic state updates during execution
Architecture
The package uses a clean, orchestrator-based architecture:
- AgentFrameworkAgent: Lightweight wrapper that delegates to orchestrators
- Orchestrators: Handle different execution flows (default, human-in-the-loop, etc.)
- Confirmation Strategies: Domain-specific confirmation messages (extensible)
- AgentFrameworkEventBridge: Converts Agent Framework events to AG-UI events
- Message Adapters: Bidirectional conversion between AG-UI and Agent Framework message formats
- FastAPI Endpoint: Streaming HTTP endpoint with Server-Sent Events (SSE)
Next Steps
- New to AG-UI? Start with the Getting Started Tutorial
- Want to see examples? Check out the Examples for AG-UI features
License
MIT
Metadata
Release files for agent-framework-ag-ui 1.0.0b260106
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agent_framework_ag_ui-1.0.0b260106.tar.gz | 84.8 kB | Without provenance | Details for agent_framework_ag_ui-1.0.0b260106.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agent_framework_ag_ui-1.0.0b260106-py3-none-any.whl | Python 3 | none | any | Details for agent_framework_ag_ui-1.0.0b260106-py3-none-any.whl |
Total release size: 147.3 kB
Release files / agent_framework_ag_ui-1.0.0b260106.tar.gz
| Download URL | agent_framework_ag_ui-1.0.0b260106.tar.gz |
|---|---|
| Size | 84.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
80a7588ad13f0b43bae28b3985d340639e4791012a802679622a0709a1b02be3
|
|
BLAKE2b-256 checksum How to use checksums |
4996a0719fec7f13c5f5d2fb5e60ed51937eba587d1cc06fac24fadc2b72caab
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.22 {"installer":{"name":"uv","version":"0.9.22","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / agent_framework_ag_ui-1.0.0b260106-py3-none-any.whl
| Download URL | agent_framework_ag_ui-1.0.0b260106-py3-none-any.whl |
|---|---|
| Size | 62.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6fc4cc8a25343b306d62e677477be9ecefa438bd1385502fcf9da66d184d7998
|
|
BLAKE2b-256 checksum How to use checksums |
c11f32e68cb30531789d62c489864b46264ada2a92581ff86801a5bcd6693833
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.22 {"installer":{"name":"uv","version":"0.9.22","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for agent-framework-ag-ui 1.0.0b260106
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.