SnapLLM: Switch between local LLM in under 1ms Multi-model&-modal serving enginegithub.com·1 pts·maheshvaikri99·2
Show HN: ISON – Data format that uses 30-70% fewer tokens than JSON for LLMsgithub.com·7 pts·maheshvaikri99·14
Show HN: MAPLE – Multi-agent protocol with resource-aware schedulinggithub.com·1 pts·maheshvaikri99·0