Agentor is an open-source framework designed for creating multi-agent pipelines. It enables secure and easy connections between LLMs and various tools like Gmail, Google Calendar, and CRMs in just minutes. Build, prototype, and deploy intelligent agents that integrate seamlessly into workflows.
Agentor is an advanced, open-source framework designed to seamlessly build, prototype, and deploy AI agents that integrate securely with various tools, including email, calendars, CRMs, and more. With Agentor, users can effortlessly connect large language models (LLMs) to essential productivity tools like Gmail and Google Calendar in just a matter of minutes.
Initiate conversations about your important data with simple commands:
agentor chat
Ask questions like:
Integrate Agentor in applications using its API:
from agentor import agents
# Basic agent functionality
result = agents.run_sync(
"Find emails from GitHub about security issues", tools=["search_gmail"], max_turns=3
)
print(result)
# Advanced commands with specific tool usage
result = agents.run_sync(
"What's my schedule conflicts next week?",
tools=["list_calendar_events", "search_gmail"],
model="gpt-5-mini", # Override to specific model
)
Agentor places a strong emphasis on user data security with:
For a multi-user application model, supportive mechanisms via OAuth authentication are available. This allows users to browse their emails and calendar events securely:
from agentor.integrations.google import CredentialRecord, UserProviderMetadata, UserInfo
... # Setup code omitted for brevity
Agentor is actively evolving, with features in development including:
Agentor is an efficient solution for anyone looking to streamline workflows and enhance productivity through intelligent agent interactions. Its commitment to security and ease of use positions it as a go-to framework for developing AI applications.
No comments yet.
Sign in to be the first to comment.