6 agents with 20+ subagents each, running open-weight models on an 8GB M2 Mac
JensHonack · x · 2026-10-15
sigdel29 showcases an agent setup running 6 agents (each with at least 20+ subagents) on a mere 8GB Mac M2, all on open-weight models via a custom harness. Kimi K3 orchestrates, Qwen handles per-ticket subagents, GLM 5.1 implements code, routed through Neuralwatt—and was used to build their Android app.
Related event: Agent Loop on an 8GB M2 Mac Ships an Android App in a Weekend(2 posts)→
More from coding & agent
- Neon ships official AI Gateway adapter for TanStack AI with single-credential multi-model access — matei_zaharia · 2026-10-23
- Reflection AI's Beam agent auto-builds a Gemma-4 fine-tuning notebook, boosting accuracy 66.5% — danielhanchen · 2026-10-23
- Cua Spaces SDK lets Hermes and other agents run in sandboxes on your own hardware — Teknium · 2026-10-23
- PHP hit by two unauthenticated RCE flaws; ProjectDiscovery launches free internet-wide alert service — cyb3rops · 2026-10-23
- Modal open-sources Spindle, a Tinker-compatible training server that charges GPU time instead of tokens — josh_wills · 2026-10-23
- Testing the Azure Cosmos DB Agent Kit: what it found reviewing a Claude-built app, in RUs saved — adnan_hashmi · 2026-10-23