ag_ui_adk
ADK Middleware for AG-UI Protocol
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained, has no security vulnerabilities, low install friction, and a permissive MIT license. Install it if you are building an agent application that needs to bridge Google ADK agents with AG-UI's protocol—it is purpose-built for that integration. If you are not using both ADK and AG-UI, it is not applicable.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later (supports up to 3.14).
- Requires a Gemini API key exported as GOOGLE_API_KEY environment variable to run examples.
- Low friction install with a pure-Python wheel.
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions—suitable for most projects.
last release 2026-06-23 (52 days) · last repo commit 2026-08-14 · 15,315 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 169,213 downloads/mo, #10,427 on PyPI
Alternatives
Verify before relying
pip install ag-ui-adk
from ag_ui_adk import ADKAgent
from google.adk.agents import Agent
my_agent = Agent(name="assistant", instruction="You are helpful.")
agent = ADKAgent(adk_agent=my_agent, app_name="my_app", user_id="user123")
async for event in agent.run(input_data):
print(f"Event: {event.type}")- Whether the 271 comprehensive tests mentioned in the description are included in the PyPI distribution or only in the source repository.
- Performance characteristics and scalability limits for concurrent agent runs or high-volume tool calls.
- Whether ResumabilityConfig (HITL workflows) requires google-adk >= 1.16.0 as stated, and what happens if an older version is installed.
What it is and what it does
ag-ui-adk is a Python middleware that connects Google's ADK (Agent Development Kit) agents to the AG-UI Protocol, a framework for building agent-driven UIs. It translates between ADK's agent execution model and AG-UI's event-streaming interface, allowing ADK agents to power interactive frontends. The middleware handles async execution, tool invocation, and human-in-the-loop workflows where agents pause for user approval before resuming.
The package provides two main integration paths: direct usage for embedding agents in Python code, and a FastAPI endpoint for server-based deployments. It depends on fastapi, aiohttp, uvicorn, pydantic, and other async-capable libraries. The middleware is actively maintained, has no known vulnerabilities, and is designed for developers building agent-driven applications that need to bridge ADK's agent capabilities with AG-UI's protocol.
Use it for
- Deploying a Google ADK agent as a FastAPI service that streams events to an AG-UI frontend.
- Building human-in-the-loop workflows where an ADK agent pauses for user approval before executing tools.
- Integrating Gemini-powered agents into web applications using AG-UI's protocol and Dojo interface.
- Running multiple ADK agents with session management and per-user context isolation.
- Developing agent-driven UIs that combine ADK's tool calling with AG-UI's event-driven architecture.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained, has no security vulnerabilities, low install friction, and a permissive MIT license. Install it if you are building an agent application that needs to bridge Google ADK agents with AG-UI's protocol—it is purpose-built for that integration. If you are not using both ADK and AG-UI, it is not applicable.
Install
ag-ui-adk on PyPI
Before you install
Low friction install with a pure-Python wheel. Active maintenance (last commit 2026-08-14) and recent releases. Depends on 10 runtime packages including fastapi, aiohttp, and uvicorn; all are standard, well-maintained libraries.
Requires Python 3.10 or later (supports up to 3.14). Requires a Gemini API key exported as GOOGLE_API_KEY environment variable to run examples.
License in practice
MIT license permits commercial and private use with minimal restrictions—suitable for most projects.
Quickstart
pip install ag-ui-adk
from ag_ui_adk import ADKAgent
from google.adk.agents import Agent
my_agent = Agent(name="assistant", instruction="You are helpful.")
agent = ADKAgent(adk_agent=my_agent, app_name="my_app", user_id="user123")
async for event in agent.run(input_data):
print(f"Event: {event.type}")Verify before relying
- Whether the 271 comprehensive tests mentioned in the description are included in the PyPI distribution or only in the source repository.
- Performance characteristics and scalability limits for concurrent agent runs or high-volume tool calls.
- Whether ResumabilityConfig (HITL workflows) requires google-adk >= 1.16.0 as stated, and what happens if an older version is installed.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release <3.15,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 10 packagesag-ui-protocolag-ui-a2ui-toolkita2ui-agent-sdkaiohttpasynciofastapigoogle-adkpydanticsse-starletteuvicorn |
| Maintenance | Actively maintained 52 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 169,213 / month, #10,427 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: ag_ui_adk-0.7.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “google adk ag-ui integration”
- ag_ui_adkBridges Google ADK agents to the AG-UI Protocol, enabling ADK-built…
- toolbox-adkEnables Google ADK agents to natively use tools from the MCP Toolbox…
- openinference-instrumentation-google-adkAuto-instruments Google ADK applications to emit…
Give your agent the search over MCP, or paste the wish link into any chat.
More Application Frameworks packages
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.
Install it if you're developing CLI tools, dashboards, or interactive terminal applications.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.
Install it if you need to build or connect to servers.
Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.
See also ag-ui-langgraph · ag-ui-protocol · agent-framework-ag-ui · google-adk · toolbox-adk · openinference-instrumentation-google-adk · a2ui-agent-sdk · ag-ui-a2ui-toolkit · google-agents-cli · vertexai