Run Claude Managed Agents with Chat SDK
- Source
- vercel.com
- Author
- Ben Sabic
- Date
Context
Anthropic's Claude Managed Agents can supply the runtime while Vercel's Chat SDK supplies its conversational interface. The integration announcement assigns model execution, tools and session state to Managed Agents, with Chat SDK adapting the conversation to different interfaces.
In the browser quickstart, the managed session stores the conversation, so the transcript and replay can read from it without a separate application database for that history. Developers can stream replies and display tool activity while leaving the agent's execution loop and conversation persistence to the managed service.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
“Claude Managed Agents handles the agent loop server-side, including the model, tools, session state, and sandboxed web research.”
“Chat SDK gives that agent a chat interface through a single type-safe handler, with adapters that carry it to Slack, WhatsApp, and more.”
“It runs on Chat SDK's web adapter, so there's no platform registration, webhook verification, or tunnel, just your Anthropic credentials.”
Checking sign-in…
Loading comments…