cd /news/ai-agents/looking-for-collaborators-dataset-cu… · home topics ai-agents article
[ARTICLE · art-128119] src=discuss.huggingface.co ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Looking for collaborators (dataset curation / fine-tuning) — ZYR3.1MoE, open-weights multi-agent orchestration model

The developer of ZYR3.1MoE, an open-weights 9B-parameter multi-agent orchestration model built on a Qwen base, is seeking one or two collaborators for dataset curation, agent orchestration, or fine-tuning work. The model uses a layered stack — an ATP layer for planning, task decomposition, and verification, an ACN layer for inter-component messaging, and a MeO Router/Reasoner/Synthesizer that routes tasks to 11 specialist agents including Planner, Researcher, Reasoner, Coder, Math, Critic, Fact Checker, Creative, Optimizer, Reviewer, and a Computer agent. The developer says the project is currently run solo and is recruiting people with experience in tool-use datasets, agent trajectories, or MoE merges.

read1 min views1 publishedSep 13, 2026

Hi, I’m the developer behind ZYR3.1 (zyr-AGENT/ZYR3.1MoE). It’s an open weights, merged, standalone model — 9B parameters, fully self-contained (no adapter/PEFT step needed), built on a Qwen base.

The design is a layered multi-agent orchestration stack: an ATP layer handles planning, task decomposition, and verification; an ACN layer carries messages between components; and MeO (Router/Reasoner/Synthesizer) decides which of 11 specialist agents — Planner, Researcher, Reasoner, Coder, Math, Critic, Fact Checker, Creative, Optimizer, Reviewer, and a Computer agent — get involved for a given task. Simple questions skip the orchestration entirely and go straight to the base model; only real work requests trigger the full plan → route → build → verify loop.

I’ve also been careful to separate trained behavior from real execution — there’s a demo trace showing the simulated “team chat” style the model produces, and a separate, genuinely externally-verified trace (real commands, real exit codes, real pass/fail) so people can see the difference rather than take marketing copy at face value.

I’m running this solo right now and looking for one or two collaborators who enjoy dataset curation, agent orchestration, or fine-tuning work — especially if you’ve worked on tool-use datasets, agent trajectories, or MoE merges. Happy to go deep on the architecture or the eval setup with anyone interested.

Model card: zyr-AGENT/ZYR3.1MoE · Hugging Face

── more in #ai-agents 4 stories · sorted by recency
── more on @zyr3.1moe 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/looking-for-collabor…] indexed:0 read:1min 2026-09-13 ·