UPDATE – 13/07/26:

1) We have added a repository reproducing the methods.

2) We have commented on output quality in the post (in addition to tokens/cost).

3) Per a previous update, we now handle Fable 5 in the post.

UPDATE:

After reading PUSH_AX's valid comment: ``` This is like saying contractor (A) asked for $33,000 to undertake the work and contractor (B) asked for $7,000 Are we measuring and caring about the right thing? ``` We will update the post to include:

1) A more in-depth task. 2) Qualitative results comparison. 3) As soon as possible, a reproduction of the inputs and outputs.

This isn't accurate since the main reason I'm using Claude Code instead of these other interesting sounding harnesses is the subscription service with highly discounted token usage. With OpenCode, you're paying the full price.

Therefore, you should include the actual costs associated with the task in API token usage or subscription level. Is there a reasonable way to do apples to apples cost comparison?

We are using Claude Max with OpenCode. See the post for details.

If cost were the only factor of course you'd use B, but presumably you also care about quality quite a bit.

Thanks, I'm looking forward to this!

I wonder if a lot of the 33k is context, like from recent conversations.

We've updated the post now!

Thank you!

Anecdotally, the results from OpenCode + Claude appear to be the same if not better for our uses over the past year.

We have never read your blog or your content before.

Suspect that many have covered the "Comparing agentic coding tools" angle before, and that the differentiator is depth of analysis + conclusions.

We are yet to try Pi!

Model:

Cost, mainly. The runs went through a Claude Max subscription rather than metered API billing, and pinning an older stable snapshot kept run-to-run comparisons clean and cheap. The fixed harness payload (system prompt plus tool schemas), so the headline numbers shouldn't change too much.

That said, happy to re-run the matrix on Fable and publish the diff; payload figures should barely move, tool-calling behaviour might.

Gateway:

Meridian (github.com/rynfar/meridian); proxy that bridges the Claude Code SDK to a standard Anthropic endpoint so a Claude Max subscription can drive OpenCode-et-al.

It's the auth route for all agent traffic on the machine, not something built for the benchmark.

Is this allowed under Apple's ToS?

I recall the Beeper Mini debacle not so long ago, and fear that this may be a house built on sand.

Apple is not necessarily against programmatic messaging. In fact, they actually developed Applescript for people to do so. Beeper was using it to replace the iMessage interface when it already exists, which is why I think Apple was against it. We're doing something fundamentally different - allowing agents to interact with humans on iMessage, which is something that the current iMessage interface cannot do.

Apple were against Beeper because it opened their platform to people who weren’t Apple-sanctioned users.

Apple might have cited a different technical reason but that would only have been to avoid antitrust regulations.

Unfortunately for you, this startup idea also allows non-sanctioned entities access to iMessage. So Apple will ban your access to.

How does this differ to Mastra?

Mastra is a business, this seems to be a helpful lib

One big difference seems to be Mastra has tests and this project doesn't.

As the entire planet now knows, the Claude Code source leaked on March 31.

The engineering-focused findings have been covered extensively (fake tool injection, Undercover Mode, KAIROS, etc).

This piece focuses on what these findings mean if you're using Claude Code to build AI systems subject to the EU AI Act.

TL;DR / spoiler:

Claude Code isn't a high-risk AI system in and of itself.

The EU AI Act regulates your deployed system and your process, not your tool vendor's internal engineering practices.

How does this differ to Open Code Desktop?

This doesn't support Linux where Open Code does.