Loading video...

Video Failed to Load

Go Home

Introducing: Granola CLI/Claude Code Skill/OpenClaw and Hermes skill from the Printing Press printed by Damien Stevens . - Cross-meeting SQLite search - MEMO pipeline runner - Attendee timelines - Stop the MCP logged-out pain Really excited about this one. I can't live without Granola I may have told Damien...

35,421 views • 5 months ago •via X (Twitter)

45 Comments

Damien Stevens's profile picture
Damien Stevens5 months ago

@meetgranola @ppressdev @mvanhorn Love how easy printing press could learn from my hours of trying to get Granola to work well + do latest web research to gain insights from others. It feels like you infused my learning + community learning into one command!

Justin Miller's profile picture
Justin Miller5 months ago

@meetgranola @ppressdev @damienstevens Awesome to see Granola support!

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens the best

Onee's profile picture
Onee5 months ago

@meetgranola @ppressdev @damienstevens Hi, You should add HeyGen CLI and Hyperframes CLI here:

jinjingliang's profile picture
jinjingliang5 months ago

@meetgranola @ppressdev @damienstevens yummy

Trevin Chow's profile picture
Trevin Chow5 months ago

@meetgranola @ppressdev @damienstevens Wooooo. Nice.

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens Woohoo 🙌

Addison's profile picture
Addison5 months ago

@meetgranola @ppressdev @damienstevens My god! He's done it again!

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens I didn't even do it! Open source is wild. Someone printed it!

Addison's profile picture
Addison5 months ago

@meetgranola @ppressdev @damienstevens I know!

Adi Singh's profile picture
Adi Singh5 months ago

@meetgranola @ppressdev @damienstevens incredible, cant believe you ship this fast

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens Wasn’t even me! #community

Eren Suner's profile picture
Eren Suner5 months ago

@meetgranola @ppressdev @damienstevens If you are wondering how other agents are using your skills take a look at Yea I made it but I pinky promise it’s good - also free :))

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens love the design!

Eren Suner's profile picture
Eren Suner5 months ago

@meetgranola @ppressdev @damienstevens Thank you :))) want to try it?

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens I will check it out

Emily Brown's profile picture
Emily Brown5 months ago

@meetgranola @ppressdev @damienstevens Very cool workflow upgrade for MeetGranola users. Native CLI + skills for Claude Code, OpenClaw, and Hermes Agent with cross-meeting search and attendee timelines makes meeting memory far more usable. Printing Press keeps shipping useful agent-native tools fast.

hira's profile picture
hira5 months ago

@meetgranola @ppressdev @damienstevens this is next level stuff right here

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens Thx 🙏

Jeffrey Sperling's profile picture
Jeffrey Sperling5 months ago

@meetgranola @ppressdev @damienstevens The printing press keeps on printing! 🖨️ Nice job @mvanhorn 👏 and team

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens Uh oh the 🐐 of @slashlast30days may have discovered @ppressdev

Ryan Sarver's profile picture
Ryan Sarver5 months ago

@meetgranola @ppressdev @damienstevens Bravo! Love the @ppressdev concept. Very old world meets new world

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens Right?! It’s fun

Tony Dang's profile picture
Tony Dang5 months ago

@meetgranola @ppressdev @damienstevens Let's go!! The press keeps printing :)

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens Thanks Tony !!!

@rizk-taker's profile picture
@rizk-taker5 months ago

@meetgranola @ppressdev @damienstevens Genuinely curious - why granola still over open source? OpenOats, etc

Mairtini's profile picture
Mairtini5 months ago

@meetgranola @ppressdev @damienstevens Can’t wait to try it. Do you ever sleep.

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens I didn’t even do anything. Community !

Damien Stevens's profile picture
Damien Stevens5 months ago

@meetgranola @ppressdev Nice video @mvanhorn, what did you use to produce it?

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev Hyperframes by @HeyGen. Big fan!

Ben Eidelson's profile picture
Ben Eidelson5 months ago

@meetgranola @ppressdev @damienstevens awesome

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens Thx Ben!

Crypto's profile picture
Crypto5 months ago

@meetgranola @ppressdev @damienstevens This looks powerful. The SQLite search and MEMO pipeline will transform meeting workflows. Great work integrating Hermes.

Timur Yessenov's profile picture
Timur Yessenov5 months ago

@meetgranola @ppressdev @damienstevens @mvanhorn this is the kind of skill that makes agents feel useful instead of generic. meeting memory needs boring infra though: SQLite/search provenance, refresh rules, and a clear line between notes the agent found vs conclusions it inferred.

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens Yesssss

Marco Lobo's profile picture
Marco Lobo5 months ago

@meetgranola @ppressdev @damienstevens No api key? So it also works without a subscription?

Felix Shpilman's profile picture
Felix Shpilman5 months ago

@meetgranola @ppressdev @damienstevens Random question. Can this cli understand whether a recording was started? Im trying to build a reminder bot in telegram to push me to turn on the recording.

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens It doesn’t but file an issue or pr and maybe it could!

Mat Silverstein's profile picture
Mat Silverstein5 months ago

@meetgranola @ppressdev @damienstevens ooh i've gotta create one for then, open source local first meeting agent ftw

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens 👀

vu's profile picture
vu5 months ago

@meetgranola @ppressdev @damienstevens @ppressdev doesn't get enough love

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@meetgranola @ppressdev @damienstevens Thx sir

Adonis Cyril | Tech + AI's profile picture
Adonis Cyril | Tech + AI5 months ago

@meetgranola @ppressdev @damienstevens wait can you get the transcripts on the free version of granola as well?

Matt Van Horn's profile picture
Matt Van Horn5 months ago

@adoniscyril @meetgranola @ppressdev @damienstevens I haven't tried, but the work-around that the @ppressdev built does not require an API key - so probably would work. Give it a whirl?!

Alex Plav's profile picture
Alex Plav5 months ago

@meetgranola @ppressdev @damienstevens Thank you!!!

Related Videos

Everyone keeps talking about the possibilities of making money with Openclaw, but nobody actually shows you how So, I made a skill for your Openclaw that transforms it into a one-man AI real estate marketing machine. This skill took me 2 weeks, 50+ hours and ~$800 in API credits to make With this skill, your Openclaw will autonomously make videos like the one below by simply scraping images from listings No approval gate. Fully autonomous. Output decided by your CRONs cadence. It's exactly what mine does, and that's exactly what you should be doing with yours. Run the CRON once a day; if you sell at least one video, you should make $300-$800 each. Also: total cost per video: ~$5.00 I truly believe this skill is one of the most practical ways you can actually make money with Openclaw in the lowest effort way possible. Most people will read this, maybe bookmark the tweet, and never take action. All I hope is that one of you guys actually takes action and makes money with this. Because of how long this skill took me to make, I'm only giving the entire thing away to my paid Subscribers on Twitter. You'll also have direct access to me for any troubleshooting + any other Skills I make like this in the future (one more dropping this week)! You just have to feed it to your Openclaw and link a few API keys. This will be the first of many Openclaw skills/overpowered AI that I only offer to my Subs! Full Skill + a lot more is waiting for you here for $25/m:

ashen

23,148 views • 6 months ago

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇

YanXbt

23,088 views • 3 months ago