My global CLAUDE.md/AGENTS.md etc have strict rules to never use subagents without approval or when specifically requested except for whitelisted scenarios.
I've taken a bit longer than I wanted but it will be open sourced soon.
It's a durable orchestration engine that takes in specs/requirements and coordinates agents externally (meaning the engine drives the loop, not an agent) until the work is fully implemented/verified and reviewed.
It's meant to be used with any harness as basically the last step. You plan your work with whatever LLM you use and then hand off implementation to the engine (through an MCP server or other surfaces)
It can use your OpenAI/Anthropic subscriptions or any other provider and you can mix and match models across implementation and review in any way you want with fan out for parallel reviewers and more.
The goal is to produce high quality unsupervised code that matches your requirements and is reviewed throughout the implementation rather than at the end only, so that mistakes don't compound.
OpenRouter Fusion is basically ask N models + synthesizer step.
This is ask a special orchestrator they built, which is in front of a bunch of models, which model would suit the request best.
Regular Fugu seems to be just "pick the best model and route the request there"
Fugu Ultra can generate like a little mini workflow/plan instead to achieve a result
1. Ask GPT to derive the math.
2. Ask Opus to check for implementation/security issues.
3. Ask Gemini to synthesize or resolve disagreement.
4. Return final answer.
I could be wrong but seems to be that at a glance, so I think it's more dynamic than OpenRouter Fusion.
Gonna give this the biggest compliment and highest honor I give alternative hacker news interfaces: I don't hate it!
I really like the simplicity of HN and this kinda keeps it (somewhat) in a way that I like.
When the comment overlay is open however, I was expecting tapping outside of it to close the overlay btw, not to let me tap the underlying stories and get redirected.
That's a really fun project! What kind of issues are you facing that requires that much rework? Is it that the manufacturing of the book wasn't precise enough and the mini demos don't work perfectly?
Beyond the target age of your book but when I was 7-8 years old my favorite book was a science book that had interactive experiments. Hope your book leaves the same kind of positive and memorable impression on kids.
It's a durable orchestration loop for implementing code with LLMs that forces review and verification gates until the code matches exactly what you asked for.
It's complementary to any existing harness or tools you use, you investigate and plan your work and simply have your agent hand off the implementation to the engine.
You can have Opus 4.8 implementing, GPT 5.5 and DeepSeek reviewing in different roles etc, mix and match however you like.
It also supports sandboxing out of the box, starting with the YC backed Microsandbox.
There's an often hard to express subjective experience you get with a new model, especially if you spend a lot of time trying out different ones.
I believe the people who feel like Fable is a big improvement, for me it's just much more reasonable and grounded.
It makes me realize how much of a try hard over optimizing planner GPT 5.5 can be. I've been fighting it often to simplify plans.
But no matter the model you can't trust them to actually deliver on very long tasks while maintaining quality. At least not without external orchestration and review.
It's meant for the implementation of well defined tasks/specs while orchestrating a review/fix/verify loop.
Every day I have implementations running for hours non stop, it's simply the time it takes to get a proper and well reviewed implementation with LLMs imo.
From what I've read so far it's less about Mythos being much better at tasks in isolation.
Security wise, it's about being able to find and chain multiple vulnerabilities to actually create viable exploits.
So I would imagine that if you were using it for regular software development you may not feel that it's that different unless used in a particular way?
x.com/alasano