正在加载视频...

视频加载失败

Hermes Agent. Zero to full autonomous operation. One complete course. Installation. Skills. Memory. MCP. Scheduler. Multi-agent. Works while you sleep. The people who build this system will never manually operate a content, research, or business workflow again. The compounding starts from the first automated skill that runs. Read this...

180,023 次观看 • 5 个月前 •via X (Twitter)

33 条评论

Eugeniu Ghelbur 的头像
Eugeniu Ghelbur5 个月前

Check on this: Today shipped a HUGE update

Alpha Batcher 的头像
Alpha Batcher5 个月前

right now i'm professional Hermes Agent user thanks to Cyril

Enhans 的头像
Enhans5 个月前

The self-improvement loop is what makes Hermes compelling. The question is what happens when it runs across a team instead of one person. We looked at this closely. Check our profile for the full breakdown.

Gerard Sans | Axiom 🇬🇧 的头像
Gerard Sans | Axiom 🇬🇧5 个月前

Fastest way to go token bankrupt.

Henry "Coop" Jackson 的头像
Henry "Coop" Jackson5 个月前

Guy who manually operates business workflows for a living just lost his job, they warned us about this

Yaki 的头像
Yaki5 个月前

Automation just got a whole new level, can't wait to see the impact on workflows

CyrilXBT 的头像
CyrilXBT5 个月前

I agree changing the game forever

Adel Bucetta 的头像
Adel Bucetta5 个月前

the honest answer is that what makes hermes agent so compelling isn't just its tech stack, but the implicit promise of a life where mundane tasks are taken care of without human intervention. we'll have to wait and see if the benefits outweight the potential loss of human ag

Emre Ates 的头像
Emre Ates5 个月前

@Teknium What do you say bro

sandybrige 的头像
sandybrige5 个月前

すごい技術ですね!効率が良さそうです。

Nelson Rodriguez 的头像
Nelson Rodriguez5 个月前

This is the kind of guide beginners actually need

Vik 的头像
Vik5 个月前

works while you sleep. but memory continuity after restarts is what breaks most setups.

Juice Lab UI/UX & Development Agency 的头像
Juice Lab UI/UX & Development Agency5 个月前

Sleep is starting to become a productive state.

EPICOG 的头像
EPICOG5 个月前

Hermes is turning automation into a real operating system

Laura 的头像
Laura5 个月前

This Hermes Agent setup is next level, bro. Full autonomy with skills, memory, and scheduler running while you sleep—compounding from day one. Bookmarking hard.

aira 的头像
aira5 个月前

works while you sleep is the demo. wakes up with an audit trail is the product.

Bryän 的头像
Bryän5 个月前

Crazy how fast this went from “cool side project” to “possible OS for workflows”. If Hermes really compounds from the first automated skill, the real leverage isn’t just time saved, it’s how many parallel bets you can run on content, research, and business ideas while you sleep.

MrGreen.eth 的头像
MrGreen.eth5 个月前

Wow great! curious how you handle it when the agent learns something wrong is there a clean way to correct it or do you just re-ingest?

Lalli 的头像
Lalli5 个月前

The future belongs to people who automate before everyone else

dllr 的头像
dllr5 个月前

alpha right here

Kai🔺 的头像
Kai🔺5 个月前

i need to see more details about this hermes agent thing

AJ - e/acc ⚡ 的头像
AJ - e/acc ⚡5 个月前

The sleep consolidation is underrated. Mnemosyne compresses old memories into summaries so your agent gets smarter over time instead of drowning in context. Been running it for a month, one of the best Hermes plugins.

Haim Bender 的头像
Haim Bender5 个月前

try it with this

Ley 的头像
Ley5 个月前

This Hermes Agent guide is actually really good. It goes from zero all the way to full autonomous setup. Installation, skills, memory, MCP, scheduler, multi-agent workflow, everything is covered. The "works while you sleep" part hits different. Once agents start compounding on their own, manual work starts feeling so 2025.

David Pate 的头像
David Pate5 个月前

nghe ngon nhưng auto chạy sai thì toang à bác

JMoon 的头像
JMoon5 个月前

the scheduler + multi-agent combination is where it gets interesting. most people stop at single-agent MCP and miss why the architecture matters.

ōpt-ōut fīat 的头像
ōpt-ōut fīat4 个月前

awesome

Kaff 📊 的头像
Kaff 📊5 个月前

That's incredible, automating workflows can be truly life-changing, freeing up time for more strategic work.

The Crypto Wiz 的头像
The Crypto Wiz5 个月前

The real tell is when scheduler, memory, tools, and multi-agent work stop feeling like features and start feeling like the operating system. Manual workflows are going to age fast.

Cry✨Star 的头像
Cry✨Star5 个月前

alpha right here

𝘿𝙖𝙫𝙞𝙙 ✦ 𝙈𝙂𝙏 的头像
𝘿𝙖𝙫𝙞𝙙 ✦ 𝙈𝙂𝙏5 个月前

running something close to this in prod. The scaffolding takes an afternoon once you commit to it. What doesnt automate is the voice and judgment layer, you still write that by hand. Everything else is basically dictation at that point

Michael Stan 的头像
Michael Stan5 个月前

"Full autonomous operation" means something very specific until something breaks and you find out exactly what it actually meant.

Radar 24h 的头像
Radar 24h5 个月前

Sounds like the future is here! Can't wait to see what else this system can do.

相关视频

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 次观看 • 4 个月前