The agentic rag, wrung out.
Guides & WorkflowsSaturday, October 10, 2026
Feature present since v0.21.0. Enabling continuity carries the latest substantive output into the next run so monitors, news scouts, and recurring research avoid starting from zero. Silent replies possible when nothing new; failures still alert.
Directly improves reliability of scheduled agent work — a common production pattern.
Guides & WorkflowsOct 18
Long-running user shared a working pattern: keep only high-value facts in memory, dump the rest to vault or skills; nightly cron that reviews sessions and tidies skills/memory; separate script-only cron for backups. Separately, clear tip: install skills via `hermes skills install` with the SKILL.md URL rather than manual file copy. `/bro` community skill for plain-language re-explanation also circulating.
Guides & WorkflowsNov 2
Hermes Super-Intel demonstrated `/learn` turning source material (deploy steps, API docs, PDFs/books) into reusable skills. Large sources become knowledge-base skills with core ideas upfront and chapter files loaded on demand. Write-approval gate available for review.
Guides & WorkflowsSep 25
Detailed four-step walkthrough from HermesWatcher on turning a Hermes agent into a reliable autonomous worker using cron + Skills + progress files. Example: release-scout job that checks GitHub releases every six hours and produces sourced briefs without human intervention.
Never miss a night
One feed for everything, or one per agent harness you run. Rebuilt every night, with full credit on every item.
