Getting started on AGW

What is AGW?

Fri, 25 Sep 2026 00:00:00 +0000

AGW is a self-hosted agent workspace for individuals and small engineering teams. It can also serve as an agent gateway. A shared interface brings together custom agents and external agents such as Claude Code, Codex, and Pi, with conversations and execution records organized around projects.

AGW Desktop chat: select a Project and Agent, then enter a message.

Core concepts

Concept	Purpose
Model Provider	Connect a provider and model into a usable model configuration
Agent	Configure instructions, a model, and capabilities, or connect an external agent
Project	A task space containing working directories, context, and conversations
Chat	Start interactive execution, inspect messages and tool activity, and answer human input requests
Agentflow	Connect nodes into an executable workflow
Job	Trigger an agent or agentflow once, at an interval, or on a Cron schedule

See Core concepts for the distinctions and how they work together.

Core concepts

Fri, 25 Sep 2026 00:00:00 +0000

In AGW, models provide reasoning, agents organize instructions and capabilities, and Projects provide a workspace. Use Chat to interact with an agent, Agentflows to orchestrate steps, and Jobs to schedule execution.

Models and Model Providers

Model configuration has three layers:

Concept	What it describes
Provider	The model service protocol, endpoint, and authentication
Model	The model identifier, context window, maximum output, and other specifications
Model Provider	A link between a model and the service providing it, selectable by an agent

For example, you can link the same model to different Providers, then choose the actual connection for an agent. See Model providers for configuration.

Install and configure Server

Fri, 25 Sep 2026 00:00:00 +0000

AGW needs a running Server and a client to operate it. For a first local installation, choose Desktop Full. If Server already exists, use Desktop Client or a browser. After installation, configure a model service or external agent to start a conversation.

Installation paths

Method	Best for	Key differences
Desktop Full	A local graphical workspace	Installs both the desktop client and Server; Server runs as a current-user background service
Desktop Client	Connecting to an existing Server	Installs only the desktop client, without Server; connects to a local or remote Server
Docker	Containerized self-hosting	Runs Server in a container with Web included; mounts provide persistent data and workspace access
Portable Server	Hosting directly on a machine	Runs the Server executable directly with Web included; no Docker or desktop client required
Source	Development and debugging	Build and run the backend and required clients yourself to modify code and debug modules

Desktop

Open GitHub Releases.
Select Full or Client for your platform. Windows and Ubuntu currently support x64; macOS supports x64 and arm64.
Complete initialization on the first Full launch, or connect Client to an existing Server.

Full and Client share an application identity and are mutually exclusive variants. Full installs a current-user Server daemon; closing Desktop does not stop it. Packages are currently unsigned and not notarized.

Start your first conversation

Fri, 25 Sep 2026 00:00:00 +0000

Prerequisites: initialization is complete, the management UI is accessible, and you have model provider credentials. This path creates a custom agent and does not require an external CLI.

1. Set up a model connection

Open model management and configure the three items below. The form layout may vary by client, but the information is the same.

Setting	What to prepare	Purpose
Provider	The service’s protocol, API endpoint, and API key	Where AGW sends requests and how it authenticates
Model	The exact model ID, context window, and maximum output length	Which model to use and its content limits
Model Provider	A link between the model and provider	The working connection an agent selects

Use the model ID supplied by the service. Model discovery may suggest 256,000 / 64,000 for context and output limits; replace these defaults with the model’s actual specifications. See Model providers for field details.