Self-hosted workers are becoming critical infrastructure for AI agent workloads. When you're running agents that need to interact with external services - web scraping, API orchestration, browser automation - you hit Cloudflare's execution limits fast. The 30s CPU time on the free tier and even the 15min on paid plans don't work for long-running agent tasks.
The isolation model here is interesting. For agents that need to handle untrusted input (processing user URLs, parsing arbitrary documents), V8 isolates give you a security boundary that's much lighter than full container isolation. But you trade off the ability to do things like spawn subprocesses or access the filesystem.
Curious about the persistence story. Most agent workflows need some form of state between invocations - conversation history, task progress, cached auth tokens. Is there a built-in KV store or does this expect external storage?
Good use case. For state between invocations, we have KV (key-value with TTL), Storage (S3) and DB bindings (Postgres). Durable Objects not yet but it's on the roadmap.
Wall-clock timeout is configurable (default 30s), CPU limits too. We haven't prioritized long-running tasks or WebSockets yet, but shouldn't be hard to add.
nice, KV + Postgres covers most of our use cases. the TTL on KV is useful for caching auth tokens between invocations without worrying about cleanup.
for long-running tasks we've been using a queue pattern anyway - worker picks up task, does a chunk, writes state to KV, exits. next invocation picks up where it left off. works around timeout limits and handles retries gracefully. websockets would be nice for real-time feedback but polling works fine for now.
will keep an eye on the durable objects progress. that's the main thing missing for stateful agent workflows where you need guaranteed delivery.