a13nDocs

Agent Foundation

The open-source, self-hosted foundation for AI agents. Deploy the managed Service, embed the Harness library in your application, or work interactively with Harness UI.

Choose your path
Service and Harness connect SDKs, the HTTP API, Console, and Harness UI with environments, memory, models, web data, and MCP connections.

Products

Service

Teams and applications

A self-hosted platform with identities, workspaces, durable execution, and saved conversations, used through Console or the HTTP API.

Get startedOverview

Harness

Python developers

A library that composes agents from instructions, tools, and capabilities and runs them in your process. Your application owns storage and access.

Get startedOverview

Harness UI

Individuals and trusted small teams

A terminal and browser workbench for working with agents in your repositories, with shared conversations, files, and terminals.

Get startedOverview

Start with a task

Deploy a shared agent platformRun Service locally and configure a modelUse your team's agentsStart a conversation on an existing platformAdd managed agents to your applicationAuthenticate, submit work, and read resultsBuild an agent in PythonRun an offline example, then add tools and modelsWork interactively in a repositoryConnect a model and use the terminal or browserGive an application file and command accessUse the same providers with or without an agent

Building blocks

EnvironmentsPortable file, command, process, and computer accessEnvdFile and process operations over the Environment Interaction ProtocolStream ProtocolTyped AG-UI events from Harness observationsLoggingStructured logs and process-wide logging setup

This site tracks main. Agent Foundation is in active 0.x development; APIs and configuration may change between minor releases.

See Contributing for source setup, the specifications for architecture contracts, and the package catalog for distributions and examples.