Skip to content
SkillModel-led2,210 tokens in use

hermes-history-ingest

Distills Hermes agent memories and session transcripts from ~/.hermes into linked Obsidian wiki pages, redacting secrets and tracking what was ingested.

3,792 stars on the repository MIT LicenseAr9av/obsidian-wiki · skills/hermes-history-ingest
pip install obsidian-wiki
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing hermes-history-ingest costs

44tokens idle
2,210tokens in use
3,042tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure23/25
  • Examples12/15
  • Output15/15
  • Size13/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 188

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers