Realtime framework for production-grade multimodal and voice AI agents.
See https://docs.wizzpert.io/agents/ for quickstarts, documentation, and examples.
Looking for the JS/TS library? Check out AgentsJS
This README reflects the 1.0 release. For documentation on the previous 0.x release, see the 0.x branch
The Agents framework enables you to build voice AI agents that can see, hear, and speak in realtime. It provides a fully open-source platform for creating server-side agentic applications.
- Flexible integrations: A comprehensive ecosystem to mix and match the right STT, LLM, TTS, and Realtime API to suit your use case.
- Integrated job scheduling: Built-in task scheduling and distribution with dispatch APIs to connect end users to agents.
- Extensive WebRTC clients: Build client applications using wizzpert's open-source SDK ecosystem, supporting nearly all major platforms.
- Telephony integration: Works seamlessly with wizzpert's telephony stack, allowing your agent to make calls to or receive calls from phones.
- Exchange data with clients: Use RPCs and other Data APIs to seamlessly exchange data with clients.
- Semantic turn detection: Uses a transformer model to detect when a user is done with their turn, helps to reduce interruptions.
- Open-source: Fully open-source, allowing you to run the entire stack on your own servers, including wizzpert server, one of the most widely used WebRTC media servers.
To install the core Agents library, along with plugins for popular model providers:
pip install "wizzpert-agents[openai,silero,deepgram,cartesia,turn-detector]~=1.0"Documentation on the framework and how to use it can be found here
- Agent: An LLM-based application with defined instructions.
- AgentSession: A container for agents that manages interactions with end users.
- entrypoint: The starting point for an interactive session, similar to a request handler in a web server.
from wizzpert.agents import (
Agent,
AgentSession,
JobContext,
RunContext,
WorkerOptions,
cli,
function_tool,
)
from wizzpert.plugins import deepgram, openai, silero
@function_tool
async def lookup_weather(
context: RunContext,
location: str,
):
"""Used to look up weather information."""
return {"weather": "sunny", "temperature": 70}
async def entrypoint(ctx: JobContext):
await ctx.connect()
agent = Agent(
instructions="You are a friendly voice assistant built by wizzpert.",
tools=[lookup_weather],
)
session = AgentSession(
vad=silero.VAD.load(),
# any combination of STT, LLM, TTS, or realtime API can be used
stt=deepgram.STT(model="nova-3"),
llm=openai.LLM(model="gpt-4o-mini"),
tts=openai.TTS(voice="ash"),
)
await session.start(agent=agent, room=ctx.room)
await session.generate_reply(instructions="greet the user and ask about their day")
if __name__ == "__main__":
cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint))You'll need the following environment variables for this example:
- wizzpert_URL
- wizzpert_API_KEY
- wizzpert_API_SECRET
- DEEPGRAM_API_KEY
- OPENAI_API_KEY
This code snippet is abbreviated. For the full example, see multi_agent.py
...
class IntroAgent(Agent):
def __init__(self) -> None:
super().__init__(
instructions=f"You are a story teller. Your goal is to gather a few pieces of information from the user to make the story personalized and engaging."
"Ask the user for their name and where they are from"
)
async def on_enter(self):
self.session.generate_reply(instructions="greet the user and gather information")
@function_tool
async def information_gathered(
self,
context: RunContext,
name: str,
location: str,
):
"""Called when the user has provided the information needed to make the story personalized and engaging.
Args:
name: The name of the user
location: The location of the user
"""
context.userdata.name = name
context.userdata.location = location
story_agent = StoryAgent(name, location)
return story_agent, "Let's start the story!"
class StoryAgent(Agent):
def __init__(self, name: str, location: str) -> None:
super().__init__(
instructions=f"You are a storyteller. Use the user's information in order to make the story personalized."
f"The user's name is {name}, from {location}"
# override the default model, switching to Realtime API from standard LLMs
llm=openai.realtime.RealtimeModel(voice="echo"),
chat_ctx=chat_ctx,
)
async def on_enter(self):
self.session.generate_reply()
async def entrypoint(ctx: JobContext):
await ctx.connect()
userdata = StoryData()
session = AgentSession[StoryData](
vad=silero.VAD.load(),
stt=deepgram.STT(model="nova-3"),
llm=openai.LLM(model="gpt-4o-mini"),
tts=openai.TTS(voice="echo"),
userdata=userdata,
)
await session.start(
agent=IntroAgent(),
room=ctx.room,
)
...|
A starter agent optimized for voice conversations. |
Responds to multiple users in the room via push-to-talk. |
|
Background ambient and thinking audio to improve realism. |
Creating function tools dynamically. |
|
Agent that makes outbound phone calls |
Using structured output from LLM to guide TTS tone. |
|
Full example of an agent that handles calls for a restaurant. |
Full example (including iOS app) of Gemini Live agent that can see. |
python myagent.py consoleRuns your agent in terminal mode, enabling local audio input and output for testing. This mode doesn't require external servers or dependencies and is useful for quickly validating behavior.
python myagent.py devStarts the agent server and enables hot reloading when files change. This mode allows each process to host multiple concurrent agents efficiently.
The agent connects to wizzpert Cloud or your self-hosted server. Set the following environment variables:
- wizzpert_URL
- wizzpert_API_KEY
- wizzpert_API_SECRET
You can connect using any wizzpert client SDK or telephony integration. To get started quickly, try the Agents Playground.
python myagent.py startRuns the agent with production-ready optimizations.
The Agents framework is under active development in a rapidly evolving field. We welcome and appreciate contributions of any kind, be it feedback, bugfixes, features, new plugins and tools, or better documentation. You can file issues under this repo, open a PR, or chat with us in wizzpert's Slack community.
| wizzpert Ecosystem | |
|---|---|
| wizzpert SDKs | Browser · iOS/macOS/visionOS · Android · Flutter · React Native · Rust · Node.js · Python · Unity · Unity (WebGL) |
| Server APIs | Node.js · Golang · Ruby · Java/Kotlin · Python · Rust · PHP (community) · .NET (community) |
| UI Components | React · Android Compose · SwiftUI |
| Agents Frameworks | Python · Node.js · Playground |
| Services | wizzpert server · Egress · Ingress · SIP |
| Resources | Docs · Example apps · Cloud · Self-hosting · CLI |