Managed agent execution
Accepts tasks through an API, runs the agent, and streams results back without requiring users to manage agent infrastructure.
Loading page…
Coding / product dossier
Runs agents through an API with model choice, sandboxed sessions, a browser, and web search.
Product brief
Managed Agents API you can use with any model. Send a task with an API call, and Click runs the agent and streams back results. Click gives you the entire agent stack over an API, with no infrastructure to manage. Sessions are created with everything your agent needs - a sandbox, browser, and web search. Agents run on a harness with the latest innovations, like deferred tool discovery to support 1000s of tools, and Code Mode to use tools with scripts.
Why we selected it
Useful infrastructure for builders deploying agents: model-independent execution, sandboxed sessions, browser access, and web search through one API. Deferred tool discovery and script-based tool use add technical depth.
Product preview saved with our daily selection
Capability scan
Only capabilities supported by the product information we collected are listed here.
Accepts tasks through an API, runs the agent, and streams results back without requiring users to manage agent infrastructure.
Provides a managed agents API described as usable with any model.
Creates sessions with a sandbox, browser, and web search.
Includes deferred tool discovery to support thousands of tools.
Provides Code Mode so agents can use tools through scripts.
Best-fit use cases
FAQ
Send the task through an API call. Click runs the agent and streams results back.
Click describes its managed agents API as usable with any model.
Sessions include a sandbox, browser, and web search.
Click includes deferred tool discovery to support thousands of tools and Code Mode for using tools through scripts.