Automating NotebookLM with Hermes Agent: From Research to Multi-Platform Content

A developer automated the process of extracting content from Google's NotebookLM by wiring it directly into the Hermes Agent, reducing a 30-minute manual workflow to about two minutes. The engineer bypassed Google's bot detection by exporting cookies from a real Chrome browser session, enabling programmatic access to create notebooks, add sources, and generate artifacts like podcasts and infographics. The solution uses a custom Python wrapper (`notebooklm-py`) that provides a CLI and API, allowing the agent to handle the entire pipeline from research to multi-platform publishing without manual intervention.

NotebookLM made the writing smarter — analyzing sources, generating podcasts, building visuals. But getting those artifacts out of Google and into my publishing pipeline still took 30 minutes of manual clicking and downloading. I fixed that by wiring NotebookLM directly into Hermes Agent. Now research turns into publish-ready content in about two minutes. NotebookLM is one of the best research tools Google has shipped. Drop in a PDF, a few URLs, or a research query and it builds a notebook — a living summary you can chat with, quiz, or turn into artifacts. But here is where it breaks for daily publishing. After NotebookLM generates a podcast, a mind map, or a slide deck, you are back to manual mode. Visit the site. Click each artifact. Download. Rename. Move to the right folder. Format for the platform you are posting to. I was spending nearly half an hour on this for every article. The AI did the creative work; I did the file management. Worse, the standard approach for automating this — browser automation via Playwright — hits a wall. Google detects headless Chromium and Firefox instantly. The login page throws "browser not secure" and you are done. Every automation script I tried failed at authentication. I needed a way to run NotebookLM from code, download artifacts programmatically, and route them into my publishing pipeline. Hermes Agent already handled the platform distribution. I just needed the bridge. The only authentication method that survived Google's bot detection was exporting cookies from my real Chrome browser. No headless browsers, no Puppeteer tricks. Just real cookies from a real session. Here is what works reliably: notebooklm.google.com in your normal Chrome or Edge google.com and notebooklm.google.com as Netscape format using any cookie-export extension storage state.json format notebooklm-py wrapper reads that state file and gets a valid token python convert netscape cookies.py — one-time setup, reusable import json, sys, datetime, urllib.parse netscape lines = open sys.argv 1 .readlines cookies = for line in netscape lines: line = line.strip if not line or line.startswith " " : continue parts = line.split "\t" if len parts < 7: continue domain, flag, path, secure, expiry, name, value = parts :7 cookies.append { "name": name, "value": value, "domain": domain.lstrip "." , "path": path, "expires": int expiry if expiry.isdigit else None, "httpOnly": "HttpOnly" in flag or "httponly" in flag, "secure": "Secure" in flag or "secure" in flag, "sameSite": "Lax" } storage = {"cookies": cookies, "origins": } with open "storage state.json", "w" as f: json.dump storage, f, indent=2 print f"Converted {len cookies } cookies, saved to storage state.json" Usage: python convert netscape cookies.py exported cookies.txt I run this once per session. 23 cookies are enough for full API access. Until Google rotates their auth, this is the only reliable path. Once authenticated, notebooklm-py exposes a clean CLI and Python API. I wrapped this into Hermes skills so the agent can create notebooks, add sources, generate artifacts, and poll for completion without me touching the browser. Create a notebook python -m notebooklm create "Philosophy Notes" → returns notebook ID Add sources — URLs, files, research queries python -m notebooklm source add <notebook-id https://example.com/article.pdf python -m notebooklm source add-research <notebook-id "Stoicism in modern productivity" Sources can be URLs, local files, Google Drive URLs, or research queries. NotebookLM processes them and builds an indexed knowledge base you can chat with. Each artifact has its own command and output format. | Artifact | Command | Output | Best For | |---|---|---|---| | Audio Overview | generate audio | MP3 | Podcasts, Telegram voice messages | | Infographic | generate infographic "cover..." | PNG | Article covers, diagrams, flowcharts | | Mind Map | generate mind-map --instructions "..." | JSON | Architecture overviews, concept maps | | Slide Deck | generate slide-deck "5 slides..." | Presentations, LinkedIn carousels | | | Quiz | generate quiz | Text | Telegram polls, engagement | Note the positional argument for prompts. --prompt does not exist for most artifacts. Infographic, slide-deck, and report accept the description as a positional string. Mind-map only accepts --instructions . Audio accepts a positional topic or nothing — it builds the podcast from your sources directly. One gotcha: --wait can time out on slow generations over 60 seconds . I always launch without waiting, get the task ID, then poll separately: Launch generation without waiting python -m notebooklm generate infographic "Dark-themed cover for article about AI research tools, ocean palette" --orientation landscape --style professional --json → {"task id": "...", "status": "pending"} Poll in a loop until done python -m notebooklm artifact poll <task id When the status flips to completed , a Google Cloud Storage URL is returned. I download that asset and route it to the right platform folder. The full flow in Hermes Agent looks like this: Source material markdown, PDFs, URLs ↓ NotebookLM notebook created ↓ Sources added → NotebookLM indexes and summarizes ↓ Artifacts generated infographic, mind-map, audio, slides ↓ Hermes downloads, compresses, renames assets ↓ Platform-specific routing: Dev.to → full article with embedded infographic Telegram → voice message audio compressed to 48kbps mono LinkedIn → carousel from slide deck PDF Medium → essay with timeline / quote cards Bluesky → dense teaser + link to full article Mastodon → threaded summary with cover image The whole sequence runs as a single Hermes skill. I trigger it with one line: generate notebooklm article for <topic . The agent creates the notebook, waits for artifacts, downloads them, compresses audio for Telegram's 20 MB limit, and writes platform drafts in parallel. No more clicking through Google UI. No more drag-and-drop. The AI generates; the pipeline publishes. Here is the core pattern I use inside the Hermes skill: python from notebooklm import NotebookLMClient import requests, os, time client = NotebookLMClient 1. Create notebook nb = client.create notebook "Stoic Productivity Analysis" 2. Add sources — mix of URLs and research queries client.add source nb.id, source url="https://example.com/seneca-essay.pdf" client.add source nb.id, source research="modern applications of Stoic principles" 3. Generate cover image infographic cover = client.generate artifact nb.id, artifact type="infographic", instructions="Dark-themed cover image for a technical article about AI-powered research tools. Ocean color palette." 4. Poll for completion task id = cover.task id while True: status = client.poll artifact task id if status.status == "completed": break if status.status in "failed", "error" : raise RuntimeError f"Artifact failed: {status.error}" time.sleep 10 5. Download cover url = status.url r = requests.get cover url open "assets/generated/cover.png", "wb" .write r.content 6. Generate audio podcast audio = client.generate artifact nb.id, artifact type="audio" audio task = audio.task id while True: status = client.poll artifact audio task if status.status == "completed": break time.sleep 10 7. Download audio url = status.url r = requests.get audio url open "assets/generated/podcast.mp3", "wb" .write r.content 8. Compress for Telegram 20 MB limit os.system "ffmpeg -i assets/generated/podcast.mp3 -b:a 48k -ac 1 assets/generated/podcast tg.mp3" The NotebookLMClient reads the same storage state.json I built from Chrome cookies. No login step, no browser puppetry. Just API calls against a valid Google session. NotebookLM is not where content starts — it is where research gets processed. My pipeline already had source material markdown drafts, PDFs, web pages . NotebookLM adds three things other tools do not: Audio Overview — two-voice podcast generated from your sources. I drop this straight into Telegram as a voice message. Compression takes a 30 MB raw file down to 7-10 MB. Voices stay clear at 48 kbps mono. Infographics — article covers and process diagrams generated from a text description. Before this I used Python Pillow locally. It worked, but every cover looked like the same template with slightly different text. NotebookLM generates unique styles per article. I just describe what I want. Mind Maps — architecture and concept maps that I embed in Dev.to and Medium articles. The output includes node coordinates in JSON, so I can render it or let NotebookLM produce the visual directly. I still write the original text. I still decide the angle and the argument. But the repetitive work — cover design, audio production, diagram drawing — moved from my desk to the agent's queue. Playwright login is dead. Every Chromium and Firefox instance I tried was detected by Google. "Browser not secure" at the login screen, every time. The cookie export method is the only approach that still works. Wrong prompt syntax. I spent an hour debugging generate infographic --prompt "..." before realizing the flag does not exist. Positional arguments only. For mind-map, use --instructions . Audio timing. NotebookLM audio generation takes 5-10 minutes. If I use --wait , the CLI sometimes times out after 60 seconds. I now always launch with --json to get the task ID, then poll in a loop until completed . Image size limits. Bluesky caps images at 2 MB. Raw NotebookLM PNGs are often 2.3-2.8 MB. I run them through ffmpeg for JPEG compression at 800px width before uploading. Yes, ffmpeg — it handles image scaling too. Content production dropped from research plus design plus publishing to research plus about two minutes. The bottleneck is no longer tooling — it is deciding what to write. NotebookLM handles visuals and audio. Hermes handles routing and platform formatting. I handle ideas. The full pipeline code is open-source: https://github.com/AzamatSafarov/hermes-notebooklm-bridge https://github.com/AzamatSafarov/hermes-notebooklm-bridge It includes the cookie converter, the one-command pipeline, a Chrome bookmarklet for one-click cookie export, and a working example of Hermes Agent integration. If you are already using Hermes, you can slot it in with two CLI commands and a cookie file. This whole pipeline runs on the LLM Wiki pattern by Andrej Karpathy — a persistent wiki that the LLM builds and maintains as you go, instead of RAG that re-discovers everything from scratch on every query. https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f file-llm-wiki-md https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f file-llm-wiki-md Dev.to https://dev.to/azamat safarov 119e17602f/ https://dev.to/azamat safarov 119e17602f/ Medium https://medium.com/@akutagorasava777 https://medium.com/@akutagorasava777 Paragraph https://paragraph.com/@azamatsafarov https://paragraph.com/@azamatsafarov