Skip to main content
Develop your agents on the Agent Server runtime. Once deployed, agents work with three primitives: assistants for configuration, threads for state, and runs for workloads. The pages in this tab cover the capabilities Agent Server provides, how to develop and structure your application, and how to secure and customize the server.

Capabilities

Develop your application

Structure your app, configure dependencies for Python, JavaScript, and monorepos, and connect agents with RemoteGraph, semantic search, TTLs, and CI/CD.

Agent Server runtime

Work with assistants, threads, runs, and cron jobs. Stream to users, pause for human review, handle concurrent input, and connect via MCP and A2A.

Auth & access control

Authenticate users, enforce resource-level access, and connect external OAuth2 identity providers.

Server customization

Add caching, custom stores and checkpointers, lifespan hooks, middleware, custom routes, encryption, and configurable headers and logs.

Tutorials

Securing and customizing your server

Operations