A modern, modular multi-agent framework for building LLM-powered applications in Python.
pip install git+https://github.com/Midsphere-AI/orbiter-ai.git Built for real-world agents
Composable Agents
Build agents from modular pieces. Mix tools, models, and behaviors freely.
Type-Safe Tools
Define tools with Python type hints. Automatic schema generation and validation.
Three Execution Modes
Workflow chains, handoff routing, and team collaboration out of the box.
Multi-Agent Orchestration
Coordinate multiple agents with swarm flows, handoffs, and shared context.
Context Engine
Manage state, prompts, knowledge, and token budgets through a unified context.
Memory System
Persistent memory backends for long-running agents. Vector, SQL, and file stores.
Get running in minutes
python
from orbiter import Agent, run, tool
@tool
async def get_weather(city: str) -> str:
"""Return the current weather for a city."""
return f"Sunny, 22°C in {city}."
agent = Agent(
name="weather-bot",
model="openai:gpt-4o-mini",
tools=[get_weather],
)
result = run.sync(agent, "What's the weather in Paris?")
print(result.text)