bahaAbunojaim

I ran Paxel to attach its report to a YC application and was wondering how I rank and what others are getting. It looks promising, but does anyone know what other cards exist?

You can check out Mysti which supports ollama, I wrote it few months ago but planning to release an update soon

https://github.com/DeepMyst/Mysti

Happy to discuss further

Thanks!

We are actively working on it, hopefully will get something out in Jan with additional providers like cursor added

This is why context optimization is going to be critical and thank you so much for sharing this paper as this also validates what we are trying to do. So if we managed to keep the baseline below 40% through context optimization then coordination might actually work very well and helps at scaling agentic systems.

I agree on measuring and it is planned especially once we integrate the context optimization. I think the value of context optimization will go beyond just avoiding compacting and reducing cost to providing more reliable agents.

That works great too. Will be adding the ability to tag another agent in a near release

copilot support was just added in version 0.2.2

UPDATE: Mysti 0.2.2 Release

Hey HN! Quick update on Mysti based on your feedback:

1- Mysti now supports GitHub Copilot CLI as a fourth provider. So you can now do Claude Code + Copilot (running GPT-5) in Brainstorm mode, or any combination of the 4 providers. Mix and match based on what catches different issues.

2- Mysti is now MIT Licensed. Switched from BSL 1.1 to MIT. 3- Better Auth UX When a CLI isn't authenticated, you now get a friendly error with one-click "Open Terminal & Authenticate" instead of cryptic CLI errors.

Thank you so much and would love to hear your feedback anytime

Very true, Claude also tend to struggle around the context window limit and after compact

I was working on a project where I tried Claude code to optimize processing of taichi Kernel and it kept using structure that didn’t work with taichi lang limitations so it kept going on a loop, did the same with codex and faced the same issue then tried to have both agents discuss it and it worked! It saved me several hours

Link fixed

Thanks! You would need to instruct the agents to follow best practices and explain it while developing. Sometimes they get messy but if you use the right instructions/persona/skills then you will get very good results

A final review from experienced developers is always recommended

Converted it to MIT so it is MIT now

I find it useful to let one agent come up with a plan after a review and another agent implementing the plan. For example, Gemini reviewing the code, codex writing a plan and then Claude code implementing it

Haven’t done Evals yet but measured on few real world situations where projects got stuck and the brainstorm mode solved it. Definitely running evals is something worth doing and contributions are welcomed

I think what really degrades the output is the context length vs context window limits, check out NoLima

Spot on

With an MCP the agent needs to write the context to be passed to the MCP then the MCP would run the underlying CLI with that context. Mysti works differently by sharing context directly with the CLIs.

UPDATE: License is now MIT! Super excited to see your contributions and feedback!

I agree and this is part of what DeepMyst is capable of doing

Done and converted to MIT

The project is now MIT!

I'm planning to add copilot, cursor and cline but feel free to contribute to the repo if you would like to do that and will look for ways to use the mini versions of the models as well when I integrate copilot CLI

Not if you optimize the context