Client SDK vs Agent SDK
People think an agent SDK is just a client SDK with more features. It is a different job. A client SDK sends one request and hands back one reply. Your code reads it, runs any tool the model asked for, and calls again. An agent SDK runs that whole loop for you, tools and all, until the task is done.
Client SDK
A kit of code that calls an AI model's API for you, in your own language.
A client SDK is a code library that calls a model's web API for you. You call a plain function in your own language, such as Python. The library builds the request, adds your key and sends it. It tries again when a call fails, and it can stream the reply as it comes. You still decide what happens next, one call at a time.
Agent SDK
A code kit that runs the agent loop for you. It calls the model and the tools.
An agent SDK is a code library that runs a whole agent loop for you. You give it a model, instructions and tools. It sends the task to the model and runs each tool the model asks for. Then it sends the result back and repeats until the work is done. Most also handle limits, memory and a log of each step.
In one line
- Client SDK
- A kit of code that calls an AI model's API for you, in your own language.
- Agent SDK
- A code kit that runs the agent loop for you. It calls the model and the tools.