Agents
coreStateful AI agents built on Durable Objects with persistent sessions and tool use.
Stateful agent runtime with memory and live sessions
Build autonomous AI systems with secure, isolated execution.
For products where AI agents plan tasks, use tools, keep state over time, and sometimes run generated or untrusted code inside a constrained environment.
Stateful AI agents built on Durable Objects with persistent sessions and tool use.
Stateful agent runtime with memory and live sessions
Isolated execution environments for untrusted or user-submitted code.
Isolated execution boundary for risky or generated code
Stateful single-threaded actors with strong consistency, storage, and WebSocket support.
Coordination and state for sessions, tasks, and updates
Serverless edge functions. The entry point for most Cloudflare apps.
Ingress, auth, orchestration, and application glue
Run any language or runtime in containers on Cloudflare's network.
Full runtime for heavier execution environments
Run foundation models and ML inference on Cloudflare's GPU network.
Inference layer for built-in model execution
Running arbitrary generated code directly in a plain Worker removes the isolation boundary this workload usually needs.
Consider: Use Sandboxes for untrusted or generated execution.
A prompt-response chatbot is not the same as an agent unless tool use or durable state is central to the design.
https://developers.cloudflare.com/agents/
https://developers.cloudflare.com/sandboxes/
https://developers.cloudflare.com/reference-architecture/diagrams/ai/ai-vibe-coding-platform/
https://build.cloudflare.dev/
Start from one of these prompts or describe your own variation on the homepage to get a primitive recommendation.
Open the explorer