Hermes + NotebookLM "Second Brain"
Pair Hermes with NotebookLM to build a self-researching, self-teaching knowledge system.
Run this workflow
See exactly what it produces before you build it.
Build this with your agent
One copy-paste hands Claude Code, Codex, or Cursor the full recipe, steps included, nothing to fetch.
Intended Use
Researchers and knowledge workers building a personal AI that continuously researches, distills, and teaches itself from new sources.
Not for
- One-off summarization tasks
- Strictly offline use (NotebookLM requires Google)
Replaces Perplexity Pro
The Stack
Tested Against
hermes@0.12.0notebooklm:2026-05Side effects & data flow
- Network
- notebooklm.google.com
- Writes
- ~/vault/research/
- Credentials
- GOOGLE_OAUTH_TOKEN
Data privacy
- google ← research sources + prompts (retention: per NotebookLM policy)
Steps
- 1
Connect the sources
Feed Hermes research output into NotebookLM and store distilled notes in Obsidian.
Eval, 1 fixture
Last passed: verified 1mo agoresearch-flowrubrictimeout 300s · max $0.1Judge: claude-sonnet-4-5 Rubric: Pass if a new markdown file is created in ~/vault/research/ AND its body cites at least one source URL.
Results
93K views, 1.4K shares on the original post.
Did this work for you?
Our CI checks the setup runs. You tell us if the whole thing worked. Tell us straight.
Related workflows
- Read your token receipts right: volume and cost are different leaderboards
- Wire GLM-5.2 into Hermes: valid route, 64k-context check, no key in config
- Pick a model with evidence: a GitHub Models bake-off that fits the free cap
- Hermes MoA: stack frontier models into one virtual model for hard turns
- Hermes /learn: author a reusable skill from a source, not by hand
- Text your own AI assistant on WhatsApp: Hermes wired to FreeLLMAPI
Liked this workflow?
Get new verified workflows in WebAfterAI, three issues a week (Tue, Thu, Sat).