0
AI agent buildersDiscontinued

AgentRunner

Visual platform for building and running AI agent workflows

AgentRunner is a beta platform for creating, testing, versioning, and deploying automation agents through a visual node editor. Teams can connect AI providers and other applications through APIs, organize agents into projects, and use run logs to inspect workflow behavior.

AGAgentRunnerProduct screenshot pending
Best for
Developers building AI-powered workflow automation
Pricing signal
Not publicly listed
Primary category
AI agent builders
Last verified
Jul 30, 2026

The decision

Should AgentRunner make your shortlist?

Start with the job, the team, and the constraints. Product fit becomes much clearer when those three line up.

Strongest fit

Who it is built for

  • Developers building AI-powered workflow automation
  • AI engineers testing and iterating agent behavior
  • Product teams deploying agents through APIs
Practical use cases

Jobs it can take on

  • Build a node-based workflow that calls an AI model
  • Version an agent while retaining a stable production version
  • Connect an agent to another application through an API
Before you choose

Know the tradeoffs

  • AgentRunner is in beta, so features may change, be removed, or experience instability.
  • The platform does not currently support moving agents between projects.
  • The beta service should not be used for confidential, sensitive, or high-risk personal data.

Inside the product

What you can actually do with it.

The core product capabilities, grouped around the work they enable.

Visual agent editor

Users construct automation workflows with nodes for inputs, outputs, text merging, model calls, and other steps.

Model connections

AgentRunner supports connecting OpenAI, Gemini, and Anthropic providers through API keys.

Versioning and run logs

Teams can create agent versions and inspect node-level inputs and outputs from agent runs.

Typical workflow

Create a project and connect the AI providers or external applications needed for the workflow. Build an agent in the node editor, define its inputs and outputs, then test and version it. Generate project API keys to run the agent from another application.

Plans and official links

Plans and accessNot publicly listed.

See the entry price, free access options, company details, and direct vendor destinations in one place.

Choosing for a real workflow?

Make the tool work with the rest of your operation.

We map the workflow, connect existing systems, choose what to buy, and build what is missing.

Discuss your workflow