Integrating live bots to demonstrate live visitor experiences is a nice touch. I got an unexpected blocker (`Default Python urllib User-Agent gets 403'd by anc.dev`) I am not able to reproduce yet. Can you expose the scripts that the agents generate?

I took a different route with https://anc.dev (scored 100 on ax-check) and rely on a wider variety of compliance tests. Beyond websites, it also audits binaries (think CLI tooling) to help inclined developers ensure their tools are discoverable by and useful to agentic systems.

You can reproduce that finding directly from python:

```

>>> request.urlopen("https://anc.dev")

[...traceback info...]

urllib.error.HTTPError: HTTP Error 403: Forbidden

```

In this case (https://agents.withgauge.com/p/runs/40be763c-4678-4677-88df-...) the agent wrote a python script to test the site, and hit the error above. We don't have a full filesystem diff viewer in ax-check.com, although we do have that in the Gauge agents product itself.

Interesting, thank you. I'll check whether a setting on CF might be interfering. The site checks headers for routing and response types, but it shouldn't affect access.

The mcp audit at https://anc.dev/ covers all flavors of mcp, including the recently launched webmcp. Remediation prompts, accessible equally by agents and humans, can help close any gaps. Usually one-shot, unless your site is crazy complicated.

What about Cloudflare’s public DNS? https://developers.cloudflare.com/1.1.1.1/setup/#1111-for-fa...

  1.1.1.2
  1.0.0.2
  2606:4700:4700::1112
  2606:4700:4700::1002

Cloudflare DNS does not block ads, it only blocks malware

For Cloudflare's definition of "malware"

I’ve deployed mcp to prod on numerous internal apps where ai-integration has been first party requirement. Obviously, agents can use an existing api, however maximum capability requires it to be well designed and documented. As many of you may have experienced, that is not something that can be assumed and improvements may be “impossible” or at least out of current scope.

That’s where mcp (and recently webmcp) have their benefits. By design, the protocols provide predictable structure that allows agents to discover and use the tools you provide.

I’ve had success using mcp variously as an agent friendly wrapper to an existing api and as a greenfield product designed for agentic workflows. Agentic workflows can string together multiple api endpoints together into a single tool call and or use their own dedicated backends.

To share my learnings, I’ve released a free tool at https://anc.dev . While It’s still very much a work in progress, I’d love dialog and constructive feedback.

Can you share a bit more about your bifrost and llama swap setup? I’m facing memory constraints and am looking for a managed model solution that will help with hot swapping loaded models and stay-warm concurrency. Ideally with prioritization.

What do you want to know? Just start llama-swap with the models i have downloaded, add llama-swap as a provider in bifrost, expose the models you want and they become available in one single endpoint you can use in anything like opencode, openwebui or anything that speaks openai.

Yes, that makes sense. Some of my models currently run in ollama while others require their own inference servers. I’m curious about custom inference servers in bifrost and the ability to orchestrate keeping some models warm in memory while evicting and cycling other models. All of which span different providers in bifrost (I think). Obviously I can get the mechanics from an agent, more wondering about any experience with something similar.