Agentor

Fastest way to build and deploy long-running AI agents—with durability, observability, and security.

Docs | Examples

JavaScript/TypeScript SDK: Gatekeeper SDK docs

Features

🚅 Quick Start

Installation

The recommended method of installing agentor is with pip from PyPI.

pip install agentor

pip install git+https://github.com/celestoai/agentor@main

Build and Deploy an Agent

Build an Agent, connect external tools or MCP Server and serve as an API in just a few lines of code:

from agentor.tools import GetWeatherTool
from agentor import Agentor

agent = Agentor(
    name="Weather Agent",
    model="gpt-5-mini",  # Use any LLM provider - gemini/gemini-2.5-pro or anthropic/claude-3.5
    tools=[GetWeatherTool()]
)
result = agent.run("What is the weather in London?")  # Run the Agent
print(result)

# Serve Agent with a single line of code
agent.serve()

Run the following command to query the Agent server:

curl -X 'POST' \
  'http://localhost:8000/chat' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "input": "What is the weather in London?"
}'

Celesto AI provides a developer-first platform for deployment of Agents, MCP Servers, any LLM application. The celesto CLI is installed automatically with agentor.

To deploy using Celesto, run:

celesto deploy

Once deployed, your agent will be accessible via a REST endpoint, for example:

https://api.celesto.ai/deploy/apps/<app-name>

Agent Skills

Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks.

Agent Skills help agents pull just the right context from simple Markdown files. The agent first sees only a skill’s name and short description. When the task matches, it loads the rest of `SKILL

... View full README on GitHub