Stories by sparacha

Show HN: Signals – finding the most informative agent traces without LLM judges

Show HN: Preference-aware routing for OpenClaw via Plano

The two agentic loops – how to build and scale agentic apps

Arch-Function LLMs promise lightning-fast agentic AI for enterprise workflows

The rise of intelligent infrastructure for LLM applications

Show HN: ArchGW – An open-source intelligent proxy server for prompts

ArchGW: Open-source, AI-native (edge and LLM) proxy for prompt traffic

Show HN: Arch GW – Distributed gateway for agents, engineered with small LLMs

Arch – intelligent application middleware for agents, engineered with LLMs

Show HN: Arch-Function: 3B parameter LLM that beats GPT-4o on function calling

Show HN: Open-source study to measure end user satisfaction levels with LLMs