StackMap
Subscribe
Explore / scale-agentex
scaleapi

scale-agentex

Scale AI's open agent platform: scaffold agents with a CLI, run them behind the ACP protocol with a dev UI, and graduate from sync chat to durable Temporal-backed long-running workflows.

455 51 Python Apache-2.0updated yesterday
Curator's take

Pick it when agents outgrow request/response: the async tier runs on Temporal, so long-running autonomous work gets durability, retries and resumability without changing your agent code's architecture — that L1→L5 'same framework at every level' pitch is the real differentiator. The local story is genuinely turnkey: ./dev.sh boots Postgres, Redis, Mongo and Temporal plus a dev UI, and `agentex init` scaffolds a working agent. NOT for a simple chatbot — that stack is heavy, and Python 3.12+/Docker are hard requirements. If you want multi-agent conversation patterns rather than deploy-and-scale infrastructure, a framework like CrewAI or AutoGen is the lighter tool. The enterprise 'zero-ops' path funnels into Scale's hosted SGP platform — fine, but know it.

Mapped by ShipWithAI editors · links verified
README.md

Agentex

Build and deploy intelligent agents with ease
Explore the docs »

Python SDK · Report Bug · Request Feature

PyPI Version Python 3.12+ License GitHub Stars

About The Project

AI agent capabilities can be understood in five levels, from simple chatbots to fully autonomous, self-driving agentic systems:

image

Today, most AI applications are limited to Level 3 (L3) and below, relying on synchronous request/response patterns. This restricts their ability to handle complex, long-running, or autonomous workflows.

Agentex is designed to be future-proof, enabling you to build, deploy, and scale agents at any level (L1–L5). As your needs grow, you can seamlessly progress from basic to advanced agentic AI—without changing your core architecture.

In this README we will start with scaffolding an L1 example just to learn the ropes. For more complicated levels, refer to the Python SDK and Docs mentioned below. Since we have documentation resources in several places, here is how to use each of them.

Resource Description
This README Getting Started: Spin up a simple agent on your local computer from scratch in minutes. This comes with a full development UI and agent server.
Python SDK Examples: Agent-building tutorials that work out of the box. These show how to build up from simple to more complex agents using Agentex.
Docs Site Concepts: More in depth details on the what, why, and how of building L1-L5 agents.

Enterprise Support: Description of how our zero-ops deployment works. Learn how to share hundreds of agents with the rest of your company. Each agent is hosted and scaled independently on cloud-agnostic infrastructure.

Getting Started

Here is what we will build together in this README. We'll start with a Hello World agent, but quickly switch to a more intelligent one!

https://github.com/user-attachments/assets/9badad0d-f939-4243-ba39-68cafdae0078

Windows Users: Please see WINDOWS.md for a complete Windows-specific guide with PowerShell commands and troubleshooting tips.

Prerequisites

Redis is required. Agentex uses Redis for streaming and messaging. You do not need to install it yourself — the Docker stack (./dev.sh / make dev) starts it for you. If you already run Redis locally it will conflict on port 6379, so stop it first (see Troubleshooting).

macOS/Linux

# Install uv (fast Python package manager) https://docs.astral.sh/uv/getting-started/installation/
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install Docker and Node.js
brew install docker docker-compose node

# Stop redis - On Mac the default redis will conflict with the redis that is

Continue your stack

What teams reach for next — and why each earns a place beside scale-agentex. Ranked by curator confidence.