hermes-history-ingest mines the data the Hermes agent keeps locally: its persistent memories and, when logging is on, its session transcripts. Memories come first because they are curated knowledge, then the sessions are read for conclusions and decisions.
Content is grouped by topic, written with summaries, confidence fields and provenance markers, and recorded in a manifest so later runs only handle new or changed files.
What You Get
- Wiki pages grouped by topic, project and technique, distilled from Hermes memories and sessions
- Tags that Hermes attached to memories carried over as wiki categories
- A manifest entry per source file and a summary block for the Hermes source
- Redaction of keys, tokens and private identifiers
Common Use Cases
- Move what a Hermes agent has learned into your Obsidian vault
- Sync only new memories and sessions after each Hermes session
- Combine Hermes knowledge with Claude and Codex histories in one wiki
- Rebuild the vault from Hermes data after a reset
What Makes It Unique
It is written for Hermes’ layout: markdown or JSON memories, dated session folders, a config file and a skills hub. It names the Hermes skills folder and hub state as sources to skip, and merges memories into topic pages so that each memory does not become its own page.
Under The Hood
The skill is instructions for the agent. It tells the agent to read the vault config and manifest, list and read files under the Hermes folder, and call the obsidian-wiki command line to sync the index, log and hot cache. It writes markdown pages and manifest entries into your vault and refreshes a QMD search index through the qmd command when one is configured. It makes no web requests of its own.