We’ve decided to open-source a multi-agent harness we use internally at YC.
We call it “QM” and it’s meant to be easy to customize, like Hermes or OpenClaw, but useful for a whole company. We use it across accounting, legal, events, and engineering (including building QM itself!).
The whole project is under an MIT license. It is cloud-first and has Slack and web UI natively.
For agentic coding, one can say:
- Unless you need Terra Ultra perf, it's always better to use a Luna model with higher effort setting (same or better performance but cheaper).
- Forget everything below Sol High, use Luna with higher effort settings here
- Forget Sol Extra High, use Terra Ultra here
- The extra cost of Sol Ultra is probably not worth it over Max
Community report: Codex may be quietly routing some gpt-5.5 xhigh sessions to gpt-5.6-sol.
Try it in Codex App/CLI:
select gpt-5.5, set reasoning to xhigh, then run the Juice test prompt.
If it returns 128, you are probably in the gray rollout.
Worth testing to see if you got it.
codex desktop app @OpenAI is crazy
i have a session with nearly 300 subagents running more than a day
thanks to @justsisyphus lazycodex
and it is just smooth as hell
no bad experience
Alrighty, everything is ready 😎
here’s an unofficial “2x Codex limits” promo from my side for you all.
meet DevSpace — an MCP connector app that turns ChatGPT into Codex.
npm install -g @waishnav/devspace
After installing, tunnel the MCP server over the internet and enjoy 2x limits.
You can use GPT-5.5 Pro, xHigh, or High for planning, then hand off the task to your local Codex/pi/opencode/cursor/claude code instance.
Or you can just use it for reviewing code written by other local coding agents
Go ahead, experiment with different workflows, and keep the feedback coming on GitHub Issues or in my DMs
And let’s thank OpenAI for being so generous by giving us separate ChatGPT and Codex limits and by being so chill around this MCP :)
Please use it sparingly, only when you run out of limits. Don’t overuse it — in the end, they do have a button to stop it 🙂
yesterday, at the Codex hackathon, i ended up solving this problem by building an MCP connector app that turns ChatGPT into Codex, sort of.
1. you get to use GPT-5.5 Pro by exposing your local dev environment to ChatGPT, so you can use 5.5 pro for planning and handover to codex to execute it
2. you get to 2x your rate limits, just like last month, because apparently ChatGPT and Codex have separate rate limits
here is the quick demo
Codex on iOS Pro tip:
How to keep you mac from sleeping
On your mac
- download amphetamine for free
- enable when codex is on
- optional: uncheck the setting to allow closing your laptop lid