research-scan 0.5.0
Verified evidence scans for a project brief: multi-query scholarly retrieval, citation-graph expansion, DOI verification. No LLM SDK — the hosting agent does the reasoning.
Verified evidence scans for a project brief: multi-query scholarly retrieval, citation-graph expansion, DOI verification. No LLM SDK — the hosting agent does the reasoning.

A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives context…
Deep research CLI harness built on Pydantic AI capabilities

Linus Torvalds released Linux 7.2 on LKML last Sunday: Well, this last week of the release was - once again - bigger than I would have wished for, but hey, with the whole "new normal" thing, if I delayed releases for that reason we'd probably never have a rel…

Windows 11 Task Manager can show per-process NPU and GPU neural engine usage, helping you determine whether an AI app runs on dedicated AI hardware or falls back to the CPU. Microsoft introduced the optional columns in updates KB5089573 and KB5094126 for Wind…