🚀 Quickstart

Stream real-time user events into your support AI agents in a couple lines of code.

⚡ Add this skill

One command

Add the shared Autoplay SDK foundation skill for credentials and live-activity reads.

CLI

uvx --from autoplay-sdk autoplay-install-skills

View the docs →

Agent onboarding

Fetch this skill directly so your coding agent gets the same Autoplay SDK setup instructions.

cURL

curl -s https://developers.autoplay.ai/autoplay-core/SKILL.md

View the skill →

Install the SDK

Prerequisites — Python 3.10 or later required.

Mac / Linux

Check your Python version:

python3 --version

If Python is not installed, download it from python.org or install via Homebrew:

brew install python3

Then create and activate a virtual environment before installing:

python3 -m venv .venv
source .venv/bin/activate

Windows (PowerShell)

Check your Python version:

python --version

If Python is not installed, download it from python.org and run the installer — check “Add Python to PATH” during setup.

Then create and activate a virtual environment before installing:

python -m venv .venv
.venv\Scripts\Activate.ps1

If you see a permissions error, run this once first: Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser

Run this command once from your project root (with your venv active):

pip install autoplay-sdk
# OR
uv add autoplay-sdk

Install Agent skills for Cursor/Claude so your assistant follows the correct integration pattern for your stack. See Pricing for plans.

🎯 Step 1 — Connect your session replay provider

Autoplay needs a live stream of what each user is doing before anything downstream can use it as context. Pick whichever tool you already have — already wired up? The tool’s page tells you how to confirm it in seconds instead of redoing setup.

PostHog→

Connect an existing PostHog project

Amplitude→

Connect an existing Amplitude project

FullStoryComing Soon

Full setup guide coming soon

DatadogComing Soon

Full setup guide coming soon

PendoComing Soon

Full setup guide coming soon

🤖 Step 2 — Connect your AI support agent

This is where Autoplay actually does its job — giving your existing chatbot live context on what the user’s been doing, pulled over MCP the moment it needs it.

Intercom→

Connect Fin via MCP

Maven→

Connect via MCP

Ada→

Connect via MCP

Botpress→

Connect via MCP

Dify→

Connect via MCP

Crisp AI→

Connect via MCP

Landbot→

Connect via MCP

Rasa→

Connect via MCP

Inkeep→

Connect via MCP

Tidio→

Connect via MCP

Plain→

Connect via MCP

ZendeskComing Soon

Full setup guide coming soon

🗺️ What’s next

Session replay and your AI support agent are the two required pillars. Add a user tour provider as an optional extra delivery channel, or go deeper on the SDK:

Visual user tours

Trigger Pendo, Usertour, and more from the same event stream — optional

Typed payloads

Explore all fields on ActionsPayload and SummaryPayload

RAG pipeline

Embed events into a vector store in real time

MCP server

Connect any agent to pull live activity via the MCP tool

Proactive onboarding agent

Combine real-time events, memory, and golden paths

AI agent skills

Browse, install, and download Cursor / Claude skills

For structured logging and extra field conventions used across the SDK, see Logging. Release history is on the Changelog.