Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

THIS VETERAN DEVELOPER PUT 2 MAC MINIS ON HIS DESK FOR $1,198 AND TURNED HERMES INTO A LOCAL AI WORKSPACE THAT DOESN’T NEED A $210/MONTH AGENT STACK he is not flexing hardware. he is showing the part most people still miss: once Hermes runs locally, the laptop stops being... a chat window and starts acting like a workspace with memory, tools and saved skills two Mac minis, one local setup, zero cloud agent dashboard. research tasks, summaries, client notes and workflow steps stay on his machine instead of disappearing every time a session ends most people keep paying for Claude, wrappers, API calls and automation tools just to repeat the same instructions every day. Hermes cuts the waste by saving the process once and pulling it back when the same job returns the math is ugly for cloud tools. $210/month turns into $2,520/year before you even count extra tokens. his version is hardware once, local workflows after, and no panic when rate limits hit the quiet winners will not be the people with the cleanest chatbot tab. it will be the people who own the machine, the memory and the workflow before everyone else realizes that is the productshow more

Gipp 🦅

6,011 subscribers

60,173 views • 3 months ago •via X (Twitter)

News & Politics Science & Technology Finance

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

THIS 19-YEAR-OLD GIRL OPENED THE HERMES SETUP WIZARD AND SHOWED HOW A $0 INSTALL CAN TURN A $180/MONTH AGENT STACK INTO ONE LOCAL WORKFLOW she is not showing another AI logo. she is showing the boring screen that decides the whole game: provider, auth method, Claude login, Anthropic API key, local model, and where the agent actually runs most people burn money in tiny pieces. $20 on Claude, $30-70 on API calls, $25-50 on automation tools, $99 on an agent wrapper, then another $10-20 every time the workflow breaks and needs a new tool Hermes changes the math. set it up once, connect the model once, run the same type of work through one agent, and let repeated tasks turn into saved skills instead of paying tokens to explain the same process again that is where the savings actually come from. not from “free AI”, but from not rebuilding the workflow 40 times. research reports, pricing scans, customer reviews, competitor maps, client audits, all moving through the same agent layer the setup screen looks boring until you understand what it means. whoever controls the provider, the API, the memory, and the skills folder controls the whole workflow this is why Hermes is interesting. not because it looks cool on a laptop, but because it turns AI from something you rent into something you slowly build on your own machine

Gipp 🦅

13,496 views • 3 months ago

THE $599 MAC MINI GETS A $49 DOCK AND TURNS FROM A DESK COMPUTER INTO A TINY 24/7 AI WORKFLOW SERVER 00:19 he clips the dock onto the back of the mac mini, adds extra ports, ethernet, storage and turns one small silver box into a workflow hub that can stay online for 700+ hours a month a base mac mini can sit online all day, pulling light power while scripts watch folders, move files, process notes and keep boring workflows running in the background paired with claude, it becomes a small home automation box: 2-hour lectures get transcribed, 30-page articles get summarized, reports get drafted, and research gets cleaned before you even open the laptop the difference is the loop. trigger, process, verify, save, repeat. the same workflow that costs $40-100/month across cloud tools can run locally from one machine on your desk that is why this tiny upgrade matters. the dock is cheap, but it gives the mac mini enough expansion to act like a quiet server instead of another computer waiting for you to use it bookmark this before your desk setup realizes it became infrastructure.

THE $599 MAC MINI GETS A $49 DOCK AND TURNS FROM A DESK COMPUTER INTO A TINY 24/7 AI WORKFLOW SERVER 00:19 he clips the dock onto the back of the mac mini, adds extra ports, ethernet, storage and turns one small silver box into a workflow hub that can stay online for 700+ hours a month a base mac mini can sit online all day, pulling light power while scripts watch folders, move files, process notes and keep boring workflows running in the background paired with claude, it becomes a small home automation box: 2-hour lectures get transcribed, 30-page articles get summarized, reports get drafted, and research gets cleaned before you even open the laptop the difference is the loop. trigger, process, verify, save, repeat. the same workflow that costs $40-100/month across cloud tools can run locally from one machine on your desk that is why this tiny upgrade matters. the dock is cheap, but it gives the mac mini enough expansion to act like a quiet server instead of another computer waiting for you to use it bookmark this before your desk setup realizes it became infrastructure.

Gipp 🦅

73,740 views • 3 months ago

HERMES JUST GOT A CHATGPT INTERFACE AND IT IS COMPLETELY FREE. No terminal. No command line. No technical setup that takes half a day to figure out. Here is what just became possible. You can now run Hermes, DeepSeek, Ollama, and OpenClaw from a single clean chat interface. Switch between them in one click. Upload files directly. Attach knowledge bases and notes. Preview code without touching the terminal once. Use it on mobile. Make voice and video calls. All of it. Free. Open source. The setup took one conversation with Hermes itself. Pasted the GitHub link in. Hermes installed Open Web UI in Docker on its own. Connected the API server and gateway automatically. A clean ChatGPT-level interface running entirely on local hardware was live in minutes. No subscription. No data leaving your machine. No API bill at the end of the month. The people who set this up this weekend will have a local AI stack that rivals what most companies are paying $2,000 a month for in cloud infrastructure. The people who wait will keep paying for tools that send their data somewhere they cannot see. Both tools are free. Both are open source. The only thing between you and this setup is the next 30 minutes. Follow CyrilXBT for the exact config, setup steps, and local AI workflows I use to run a full stack without spending a dollar on cloud inference.

HERMES JUST GOT A CHATGPT INTERFACE AND IT IS COMPLETELY FREE. No terminal. No command line. No technical setup that takes half a day to figure out. Here is what just became possible. You can now run Hermes, DeepSeek, Ollama, and OpenClaw from a single clean chat interface. Switch between them in one click. Upload files directly. Attach knowledge bases and notes. Preview code without touching the terminal once. Use it on mobile. Make voice and video calls. All of it. Free. Open source. The setup took one conversation with Hermes itself. Pasted the GitHub link in. Hermes installed Open Web UI in Docker on its own. Connected the API server and gateway automatically. A clean ChatGPT-level interface running entirely on local hardware was live in minutes. No subscription. No data leaving your machine. No API bill at the end of the month. The people who set this up this weekend will have a local AI stack that rivals what most companies are paying $2,000 a month for in cloud infrastructure. The people who wait will keep paying for tools that send their data somewhere they cannot see. Both tools are free. Both are open source. The only thing between you and this setup is the next 30 minutes. Follow CyrilXBT for the exact config, setup steps, and local AI workflows I use to run a full stack without spending a dollar on cloud inference.

CyrilXBT

37,120 views • 5 months ago

A 24-YEAR-OLD CHINESE DEVELOPER FROM HANGZHOU TURNED RTX 4090 / 3090-CLASS GPU RACKS INTO HIS OWN PRIVATE AI CLOUD. HIS $740/MONTH AI BILL DROPPED TO $31 IN ELECTRICITY he got tired of paying for chatgpt, claude, cursor, openai api credits and every “pro” tool that quietly turns into another monthly tax. long context runs, codebase scans, document parsing, agent loops. every workflow ended with a new invoice so he built a local llm rack instead. used server hardware, RTX 4090 / 3090-class GPU boxes, ollama for automation, lm studio for testing models, llama.cpp for heavier local runs. around $6,200 upfront, but after that the cost is mostly power and maintenance now his scripts hit localhost instead of a cloud api. code reviews, private docs, chinese contracts, sql cleanup, support replies and research tasks stay inside the room. no token panic, no rate-limit wall, no sensitive files leaving his own machines the funny part is that he did not replace claude completely. he just stopped using frontier models for dumb volume work. 65% of daily ai tasks do not need the smartest model alive. they need cheap tokens, privacy and a machine that can run all night cloud ai is still the brain. local ai is the engine room. once he separated those two, his monthly ai stack stopped looking like subscriptions and started looking like infrastructure by 2027, owning your own local ai rack will not look extreme. it will look like the moment people realized renting intelligence forever was the expensive option.

A 24-YEAR-OLD CHINESE DEVELOPER FROM HANGZHOU TURNED RTX 4090 / 3090-CLASS GPU RACKS INTO HIS OWN PRIVATE AI CLOUD. HIS $740/MONTH AI BILL DROPPED TO $31 IN ELECTRICITY he got tired of paying for chatgpt, claude, cursor, openai api credits and every “pro” tool that quietly turns into another monthly tax. long context runs, codebase scans, document parsing, agent loops. every workflow ended with a new invoice so he built a local llm rack instead. used server hardware, RTX 4090 / 3090-class GPU boxes, ollama for automation, lm studio for testing models, llama.cpp for heavier local runs. around $6,200 upfront, but after that the cost is mostly power and maintenance now his scripts hit localhost instead of a cloud api. code reviews, private docs, chinese contracts, sql cleanup, support replies and research tasks stay inside the room. no token panic, no rate-limit wall, no sensitive files leaving his own machines the funny part is that he did not replace claude completely. he just stopped using frontier models for dumb volume work. 65% of daily ai tasks do not need the smartest model alive. they need cheap tokens, privacy and a machine that can run all night cloud ai is still the brain. local ai is the engine room. once he separated those two, his monthly ai stack stopped looking like subscriptions and started looking like infrastructure by 2027, owning your own local ai rack will not look extreme. it will look like the moment people realized renting intelligence forever was the expensive option.

Gipp 🦅

21,320 views • 3 months ago

WTF, THIS CHINESE FOUNDER RUNS HIS $10,000+ STARTUP'S ENTIRE WORKFLOW THROUGH HERMES AGENT ON FOUR MACHINES SIMULTANEOUSLY A studio founder just broke down why Hermes is different from every other AI tool right now: → Long-term memory. Most LLMs forget everything after the chat ends. Hermes remembers your work habits and gets sharper the more you use it. → Real execution, not suggestions. This is the core difference from Claude. Claude tells you what to do – you still do it. Hermes takes the instruction and finishes the task itself. → Scheduled tasks that just work. No complicated setup. Set the plan once, it runs on its own. This is what actual "hands-off" looks like. He's not running this on one machine. He's got FOUR laptops running Hermes simultaneously – each one handling a different part of his workflow at the same time. This is what it looks like when one person operates like a full team. He's dropping a full workflow build tutorial next – built for founders and operators trying to lighten their workload. Bookmark this, you'll want to come back to it later.

WTF, THIS CHINESE FOUNDER RUNS HIS $10,000+ STARTUP'S ENTIRE WORKFLOW THROUGH HERMES AGENT ON FOUR MACHINES SIMULTANEOUSLY A studio founder just broke down why Hermes is different from every other AI tool right now: → Long-term memory. Most LLMs forget everything after the chat ends. Hermes remembers your work habits and gets sharper the more you use it. → Real execution, not suggestions. This is the core difference from Claude. Claude tells you what to do – you still do it. Hermes takes the instruction and finishes the task itself. → Scheduled tasks that just work. No complicated setup. Set the plan once, it runs on its own. This is what actual "hands-off" looks like. He's not running this on one machine. He's got FOUR laptops running Hermes simultaneously – each one handling a different part of his workflow at the same time. This is what it looks like when one person operates like a full team. He's dropping a full workflow build tutorial next – built for founders and operators trying to lighten their workload. Bookmark this, you'll want to come back to it later.

SCOTTY BEAM

11,654 views • 2 months ago

I just tested Hermes Workspace v2 and honestly this is what Hermes should have looked like from the start. Why it matters: • Native chat with your Hermes agents • Mission control style workspace • Task boards for agent workflows • Memory and skills management • File browser and terminal in one UI • Works with local and cloud models • Runs across phone, Mac, PC, iPhone, Android If you like Hermes but hate living in the terminal, this update is for you.

I just tested Hermes Workspace v2 and honestly this is what Hermes should have looked like from the start. Why it matters: • Native chat with your Hermes agents • Mission control style workspace • Task boards for agent workflows • Memory and skills management • File browser and terminal in one UI • Works with local and cloud models • Runs across phone, Mac, PC, iPhone, Android If you like Hermes but hate living in the terminal, this update is for you.

Julian Goldie SEO

80,459 views • 5 months ago

THIS GUY OPENED A TINY PC AND SHOWED HOW A $1,800 GMKTEC EVO-X2 TURNS INTO A LOCAL AI SERVER not a cloud dashboard. not another $200/mo subscription. just one box on a desk, upgraded with storage, cleaner airflow, faster networking, and pointed at real local models. the numbers are what make it interesting. Claude Code Max is $200/mo, ChatGPT Pro is $200/mo, Cursor is another $20/mo. that is $5,040/year just to rent tools most people use for coding, research, summaries, and agents. EVO-X2 flips the setup because it has 128GB unified memory, Ryzen AI Max+ 395, and up to 110GB usable as VRAM on Linux. enough room for Qwen3-Coder 30B, Llama 70B, and 200B-class local models when speed is not the bottleneck. so the workflow becomes simple: buy the box once, install Linux, run the model locally, connect the CLI, and let the machine handle jobs from your own network instead of sending every request to the cloud. this is where the real edge starts. overnight code audits, private document search, local RAG, scraping agents, transcription, file cleanup, all running while the token meter stays at zero. frontier models still win for the hardest prompts. but for daily automation, coding, research, and private workflows, local AI is already moving from nerd setup to obvious business math. the next flex won’t be “which AI plan do you pay for?” it’ll be “what’s running under your desk?”

THIS GUY OPENED A TINY PC AND SHOWED HOW A $1,800 GMKTEC EVO-X2 TURNS INTO A LOCAL AI SERVER not a cloud dashboard. not another $200/mo subscription. just one box on a desk, upgraded with storage, cleaner airflow, faster networking, and pointed at real local models. the numbers are what make it interesting. Claude Code Max is $200/mo, ChatGPT Pro is $200/mo, Cursor is another $20/mo. that is $5,040/year just to rent tools most people use for coding, research, summaries, and agents. EVO-X2 flips the setup because it has 128GB unified memory, Ryzen AI Max+ 395, and up to 110GB usable as VRAM on Linux. enough room for Qwen3-Coder 30B, Llama 70B, and 200B-class local models when speed is not the bottleneck. so the workflow becomes simple: buy the box once, install Linux, run the model locally, connect the CLI, and let the machine handle jobs from your own network instead of sending every request to the cloud. this is where the real edge starts. overnight code audits, private document search, local RAG, scraping agents, transcription, file cleanup, all running while the token meter stays at zero. frontier models still win for the hardest prompts. but for daily automation, coding, research, and private workflows, local AI is already moving from nerd setup to obvious business math. the next flex won’t be “which AI plan do you pay for?” it’ll be “what’s running under your desk?”

Gipp 🦅

13,365 views • 3 months ago

A CHINESE LAB VISUALIZED 2,000 NEURONS AND 1,191,000 SYNAPSES IN 3D. HERMES AGENT HIT 140,000 STARS RUNNING THE SAME NETWORK LOCALLY FOR $0 hermes is the first agent that writes its own skills from experience. complete a task once and it saves the procedure as a markdown file for next time agents with 20+ self-created skills complete similar tasks 40% faster than fresh instances. less time and less tokens to get the same result qwen 3.6 35b outperforms last year's 120b models and runs on 20gb of memory. the intelligence that needed a data center now fits on your desk setup takes 30 minutes. install lm studio, pull qwen 3.6, install hermes, point it at localhost. zero api fees, zero data leaving your machine most people pay for cloud agents that forget everything between sessions. the ones running hermes locally in 2026 will look very far ahead in 2028 bookmark this and read the article below

A CHINESE LAB VISUALIZED 2,000 NEURONS AND 1,191,000 SYNAPSES IN 3D. HERMES AGENT HIT 140,000 STARS RUNNING THE SAME NETWORK LOCALLY FOR $0 hermes is the first agent that writes its own skills from experience. complete a task once and it saves the procedure as a markdown file for next time agents with 20+ self-created skills complete similar tasks 40% faster than fresh instances. less time and less tokens to get the same result qwen 3.6 35b outperforms last year's 120b models and runs on 20gb of memory. the intelligence that needed a data center now fits on your desk setup takes 30 minutes. install lm studio, pull qwen 3.6, install hermes, point it at localhost. zero api fees, zero data leaving your machine most people pay for cloud agents that forget everything between sessions. the ones running hermes locally in 2026 will look very far ahead in 2028 bookmark this and read the article below

starmex

13,420 views • 3 months ago

HERMES AGENT + QWEN 3.6 IS CURRENTLY THE STRONGEST LOCAL SETUP MOST PEOPLE CAN RUN. Even if frontier models stopped improving tomorrow, this stack would still cover the majority of real work. Qwen 3.6 (72B and 235B) is officially supported in Hermes and brings: → Strong coding and complex refactoring → Reliable tool calling and multi-step execution → Excellent long context (128k–1M tokens) → Good structured reasoning with /goal workflows → Solid memory and session continuity Paired with Hermes memory, skills, Kanban, cron and tools — you get a fully private, self-improving agent that codes, automates and runs 24/7 without sending data anywhere. You don’t need the latest closed model to build something powerful. This is one of the strongest fully local stacks available right now — and it runs on real hardware.

HERMES AGENT + QWEN 3.6 IS CURRENTLY THE STRONGEST LOCAL SETUP MOST PEOPLE CAN RUN. Even if frontier models stopped improving tomorrow, this stack would still cover the majority of real work. Qwen 3.6 (72B and 235B) is officially supported in Hermes and brings: → Strong coding and complex refactoring → Reliable tool calling and multi-step execution → Excellent long context (128k–1M tokens) → Good structured reasoning with /goal workflows → Solid memory and session continuity Paired with Hermes memory, skills, Kanban, cron and tools — you get a fully private, self-improving agent that codes, automates and runs 24/7 without sending data anywhere. You don’t need the latest closed model to build something powerful. This is one of the strongest fully local stacks available right now — and it runs on real hardware.

YanXbt

53,423 views • 3 months ago

A CHINESE BUILDER TURNED A MAC MINI INTO A PORTABLE AI WORKFLOW BOX THAT CAN RUN 18 HOURS OFF A BATTERY 01:14 he connects the power module to the mac mini and the whole setup stops being a desk computer. now the same tiny machine can run from a battery, drive a portable display, hold extra storage and stay online away from a normal desk. that matters because most ai workflows do not need a giant server. they need a quiet machine that can keep 12-20 background jobs alive, watch folders, move files, clean notes, sync research and process inputs without babysitting. paired with claude, this becomes a portable second brain machine. 3 long lectures can turn into notes, 25 saved articles can become summaries, research folders can get organized, and unfinished drafts can keep moving while the owner is away. the edge is not raw power. it is uptime in a tiny form factor. one small box can run 500-800 micro-tasks a month, while the same workflow inside cloud tools can quietly eat $60-150/month across storage, vps and automation apps. that is why this build is interesting. the chinese guy is not showing a random charger trick, he is showing what happens when a small computer gets enough ports, power and automation to behave like a pocket-sized home server. bookmark this before every desk setup gets a battery.

A CHINESE BUILDER TURNED A MAC MINI INTO A PORTABLE AI WORKFLOW BOX THAT CAN RUN 18 HOURS OFF A BATTERY 01:14 he connects the power module to the mac mini and the whole setup stops being a desk computer. now the same tiny machine can run from a battery, drive a portable display, hold extra storage and stay online away from a normal desk. that matters because most ai workflows do not need a giant server. they need a quiet machine that can keep 12-20 background jobs alive, watch folders, move files, clean notes, sync research and process inputs without babysitting. paired with claude, this becomes a portable second brain machine. 3 long lectures can turn into notes, 25 saved articles can become summaries, research folders can get organized, and unfinished drafts can keep moving while the owner is away. the edge is not raw power. it is uptime in a tiny form factor. one small box can run 500-800 micro-tasks a month, while the same workflow inside cloud tools can quietly eat $60-150/month across storage, vps and automation apps. that is why this build is interesting. the chinese guy is not showing a random charger trick, he is showing what happens when a small computer gets enough ports, power and automation to behave like a pocket-sized home server. bookmark this before every desk setup gets a battery.

Gipp 🦅

10,641 views • 3 months ago

A GIRL BOUGHT A $599 APPLE BOX AND CUT HER AI COSTS FROM $459/MONTH TO $23/MONTH. THE MAC MINI M4 IS QUIETLY BECOMING THE CHEAPEST AI SETUP IN 2026 she didn’t buy it because it looked nice on her desk. she bought it because paying for claude, chatgpt, cursor and api usage every month was getting ridiculous the setup is simple. mac mini m4, ollama, open webui, and local models like qwen, deepseek and llama. for most daily work, that’s enough to write, code, summarize, search notes, and run private workflows without sending everything to the cloud that’s why the math looks so good. a heavy ai stack can hit $459 a month, or $5,508 a year. the mac mini starts at $599 and uses around $3 a month in electricity. if it handles even 70 to 80% of the workload, it pays for itself fast install ollama, point your tools to localhost, and the workflow changes immediately. no token stress, no rate limits, no wondering where your files are going you still keep one cloud model for the hardest tasks but once a small box on your desk does most of the work, paying full price for everything starts to feel stupid

A GIRL BOUGHT A $599 APPLE BOX AND CUT HER AI COSTS FROM $459/MONTH TO $23/MONTH. THE MAC MINI M4 IS QUIETLY BECOMING THE CHEAPEST AI SETUP IN 2026 she didn’t buy it because it looked nice on her desk. she bought it because paying for claude, chatgpt, cursor and api usage every month was getting ridiculous the setup is simple. mac mini m4, ollama, open webui, and local models like qwen, deepseek and llama. for most daily work, that’s enough to write, code, summarize, search notes, and run private workflows without sending everything to the cloud that’s why the math looks so good. a heavy ai stack can hit $459 a month, or $5,508 a year. the mac mini starts at $599 and uses around $3 a month in electricity. if it handles even 70 to 80% of the workload, it pays for itself fast install ollama, point your tools to localhost, and the workflow changes immediately. no token stress, no rate limits, no wondering where your files are going you still keep one cloud model for the hardest tasks but once a small box on your desk does most of the work, paying full price for everything starts to feel stupid

Gipp 🦅

458,361 views • 3 months ago

100 MAC MINIS ON ONE METAL SHELF. IN THE CLOUD, EACH OF THOSE RENTS FOR $120 TO $500 A MONTH. that clip is a homemade rack: wire shelving packed with mac minis, each running macos, wired into one cluster. why macs and not a normal server? two reasons. you can only build, sign, and notarize ios and mac apps on apple hardware. cloud providers know it and charge for it. and apple silicon sips power and runs near-silent, so you can stack a lot of them on a shelf in a room, not a datacenter. the rent they're escaping: a single mac in the cloud runs ~$120 to $500 a month (macstadium up to aws) one engineer documented saving $4,000+ a month by self-hosting mac minis instead of cloud ci runners a used or new mini is a few hundred dollars once, then a few dollars of electricity what a shelf like this actually runs: ios and mac build farms, render jobs, app and device testing automation, and increasingly local ai inference. own the boxes, rent nothing. the uncomfortable part: the cloud was never the only option. it was the convenient one. the people who did the math bought the shelf. the honest caveat: it's real capex up front, real heat and power, and you become the sysadmin. no rented rack means no one to call at 3am. worth it at scale, overkill for one build a week. no rack rental, no per-hour metering, no fleet you don't own. save this before your cloud invoice renews again.

100 MAC MINIS ON ONE METAL SHELF. IN THE CLOUD, EACH OF THOSE RENTS FOR $120 TO $500 A MONTH. that clip is a homemade rack: wire shelving packed with mac minis, each running macos, wired into one cluster. why macs and not a normal server? two reasons. you can only build, sign, and notarize ios and mac apps on apple hardware. cloud providers know it and charge for it. and apple silicon sips power and runs near-silent, so you can stack a lot of them on a shelf in a room, not a datacenter. the rent they're escaping: a single mac in the cloud runs ~$120 to $500 a month (macstadium up to aws) one engineer documented saving $4,000+ a month by self-hosting mac minis instead of cloud ci runners a used or new mini is a few hundred dollars once, then a few dollars of electricity what a shelf like this actually runs: ios and mac build farms, render jobs, app and device testing automation, and increasingly local ai inference. own the boxes, rent nothing. the uncomfortable part: the cloud was never the only option. it was the convenient one. the people who did the math bought the shelf. the honest caveat: it's real capex up front, real heat and power, and you become the sysadmin. no rented rack means no one to call at 3am. worth it at scale, overkill for one build a week. no rack rental, no per-hour metering, no fleet you don't own. save this before your cloud invoice renews again.

RetroChainer

21,055 views • 2 months ago

This guy put an AI data center into a box that fits on a desk It doesn't look like a serious machine It looks like a mini PC you could hide behind a monitor But with enough unified memory it can run local models, answer over your own files, power agents and keep private work off someone else's servers That sounds like a hobby setup until you look at what people are actually renting every month Claude subscription ChatGPT subscription API credits cloud GPU time usage limits private files uploaded into third-party tools For years the deal was simple: if you wanted intelligence, you rented it Now a Mac Mini M4 Pro or a 128GB AMD mini PC can handle a big part of everyday AI work locally Ollama runs the models Open WebUI gives you the chat interface Tailscale lets you reach it from your phone or laptop without exposing it to the open internet The cloud still wins for the hardest tasks But most daily AI work is not frontier research It is reading documents, summarizing files, drafting, coding helpers, search, notes and private workflows Most people will keep paying rent because it is convenient Others are realizing the assistant they rent every month can become hardware they own save this

This guy put an AI data center into a box that fits on a desk It doesn't look like a serious machine It looks like a mini PC you could hide behind a monitor But with enough unified memory it can run local models, answer over your own files, power agents and keep private work off someone else's servers That sounds like a hobby setup until you look at what people are actually renting every month Claude subscription ChatGPT subscription API credits cloud GPU time usage limits private files uploaded into third-party tools For years the deal was simple: if you wanted intelligence, you rented it Now a Mac Mini M4 Pro or a 128GB AMD mini PC can handle a big part of everyday AI work locally Ollama runs the models Open WebUI gives you the chat interface Tailscale lets you reach it from your phone or laptop without exposing it to the open internet The cloud still wins for the hardest tasks But most daily AI work is not frontier research It is reading documents, summarizing files, drafting, coding helpers, search, notes and private workflows Most people will keep paying rent because it is convenient Others are realizing the assistant they rent every month can become hardware they own save this

Asteri

12,199 views • 3 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👇

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

22,720 views • 2 months ago

ANTHROPIC JUST GOT OUTFLANKED AND NOBODY IS TALKING ABOUT IT. DeepSeek V4. Ollama. OpenClaw. Hermes. Claude Code. Five tools. One stack. Completely free. The people who put this together this weekend will have a local AI setup more powerful than what most companies are paying $10,000 a month for in cloud inference. No API bills. No rate limits. No data leaving your machine. Ever. This is not a tutorial for developers. This is a setup any builder can run in under an hour. The gap between people who know this exists and people who do not just got very expensive. Very quietly. This weekend. Follow CyrilXBT for the exact setup, config files, and prompts to make this stack actually work.

ANTHROPIC JUST GOT OUTFLANKED AND NOBODY IS TALKING ABOUT IT. DeepSeek V4. Ollama. OpenClaw. Hermes. Claude Code. Five tools. One stack. Completely free. The people who put this together this weekend will have a local AI setup more powerful than what most companies are paying $10,000 a month for in cloud inference. No API bills. No rate limits. No data leaving your machine. Ever. This is not a tutorial for developers. This is a setup any builder can run in under an hour. The gap between people who know this exists and people who do not just got very expensive. Very quietly. This weekend. Follow CyrilXBT for the exact setup, config files, and prompts to make this stack actually work.

CyrilXBT

32,507 views • 5 months ago

This girl built a $24/year AI visual setup while most creators are still overpaying $1,800 to $4,080 a year for APIs, cloud rendering and visual tools. And no, this isn’t a pre-render or a paid filter hiding in the cloud. It’s live on her laptop right now. The phone camera feeds into TouchDesigner, the movement gets turned into particles, and the whole visual reacts in real time. Most people build this the expensive way. $50 to $180/month in API usage, $40 to $100/month for cloud rendering, another $60/month for visual software, then a “small” creative workflow quietly turns into a $3,000+/year habit. Her stack cuts through almost all of that. The phone becomes the input. TouchDesigner handles the visual layer. Ollama runs the local model. The laptop does the loop without sending every experiment to someone else’s server. No cloud GPU. No API meter. No subscription chain. No project that dies when the billing page fails. Just a normal machine, a camera feed, a node graph and a local model running visuals people still assume need a paid stack behind them. The numbers are the insane part. $0 for Ollama. $0 for TouchDesigner non-commercial. 8GB+ RAM is enough to start. Around $2/month if you count electricity. That’s $24/year instead of a stack that can hit $4,080/year. The effect looks like something a studio would sell. The setup is just one girl refusing to rent the whole process every month.

This girl built a $24/year AI visual setup while most creators are still overpaying $1,800 to $4,080 a year for APIs, cloud rendering and visual tools. And no, this isn’t a pre-render or a paid filter hiding in the cloud. It’s live on her laptop right now. The phone camera feeds into TouchDesigner, the movement gets turned into particles, and the whole visual reacts in real time. Most people build this the expensive way. $50 to $180/month in API usage, $40 to $100/month for cloud rendering, another $60/month for visual software, then a “small” creative workflow quietly turns into a $3,000+/year habit. Her stack cuts through almost all of that. The phone becomes the input. TouchDesigner handles the visual layer. Ollama runs the local model. The laptop does the loop without sending every experiment to someone else’s server. No cloud GPU. No API meter. No subscription chain. No project that dies when the billing page fails. Just a normal machine, a camera feed, a node graph and a local model running visuals people still assume need a paid stack behind them. The numbers are the insane part. $0 for Ollama. $0 for TouchDesigner non-commercial. 8GB+ RAM is enough to start. Around $2/month if you count electricity. That’s $24/year instead of a stack that can hit $4,080/year. The effect looks like something a studio would sell. The setup is just one girl refusing to rent the whole process every month.

Gipp 🦅

24,423 views • 4 months ago

THIS DEVELOPER TURNED A $599 MAC MINI AND $110 OF EXTRA HARDWARE INTO A PRIVATE AI COMPUTER THAT FITS IN A BACKPACK 00:49 he takes the complete setup out of the bag, connects it to a nearby screen and restores the same desktop, files and running tools in less than a minute. instead of syncing a new laptop every time he moves, the mac mini carries the original obsidian vault, claude code sessions, local models and unfinished agent tasks between every desk. the 10,000mah battery can keep the machine running for roughly 2 to 4 hours during writing, research and file organization, or around 60 to 90 minutes under heavier transcription and local ai workloads. the full build costs close to $710 if a screen is already available. that includes the mac mini, a 55w battery, the side mount and the cables needed to connect it to an ipad, hotel tv or office monitor. one box can carry 12,000 notes, 300gb of private files and several active agents without sending the data to another cloud account or rebuilding the workspace every time he changes locations.

THIS DEVELOPER TURNED A $599 MAC MINI AND $110 OF EXTRA HARDWARE INTO A PRIVATE AI COMPUTER THAT FITS IN A BACKPACK 00:49 he takes the complete setup out of the bag, connects it to a nearby screen and restores the same desktop, files and running tools in less than a minute. instead of syncing a new laptop every time he moves, the mac mini carries the original obsidian vault, claude code sessions, local models and unfinished agent tasks between every desk. the 10,000mah battery can keep the machine running for roughly 2 to 4 hours during writing, research and file organization, or around 60 to 90 minutes under heavier transcription and local ai workloads. the full build costs close to $710 if a screen is already available. that includes the mac mini, a 55w battery, the side mount and the cables needed to connect it to an ipad, hotel tv or office monitor. one box can carry 12,000 notes, 300gb of private files and several active agents without sending the data to another cloud account or rebuilding the workspace every time he changes locations.

Gipp 🦅

30,550 views • 3 months ago

20-YEAR-OLD GUY SHOWS HOW CLAUDE API CAN TURN 500-VIEW CONTENT INTO A $40K/MONTH CLIENT WORKFLOW Not from a big agency. Not from hiring writers. Just taking the same service people sell every week and wiring Claude API into the boring middle. A topic goes in. It pulls the research, angles, outline, draft, edits, and a clean file. That is normally $500-$1,500 of freelance work per client project. The screen says around $40K/month, but the real number is the time saved. A $3K project stops being 8 hours of rewriting and becomes 45 minutes of checking before delivery. Most people use Claude to write one answer. He is showing what happens when the whole process becomes the product.

20-YEAR-OLD GUY SHOWS HOW CLAUDE API CAN TURN 500-VIEW CONTENT INTO A $40K/MONTH CLIENT WORKFLOW Not from a big agency. Not from hiring writers. Just taking the same service people sell every week and wiring Claude API into the boring middle. A topic goes in. It pulls the research, angles, outline, draft, edits, and a clean file. That is normally $500-$1,500 of freelance work per client project. The screen says around $40K/month, but the real number is the time saved. A $3K project stops being 8 hours of rewriting and becomes 45 minutes of checking before delivery. Most people use Claude to write one answer. He is showing what happens when the whole process becomes the product.

Gipp 🦅

19,254 views • 4 months ago

MOST AI AGENTS RESET TO ZERO EVERY TIME YOU OPEN A NEW SESSION. Hermes Agent was built to do the opposite. Every task compounds. Every workflow becomes reusable. Every session teaches the next one. That is the core thesis behind Hermes, and it completely changes how AI agents work. Unlike most AI agents built by software tool companies, Hermes was created by the researchers training the Hermes model family itself. Meaning: The same system used internally to generate training data is now open source and available to everyone. One install gives you access to: Claude. GPT. Grok. Local models via Ollama. Telegram, Discord, Slack, iMessage integrations. Custom skills. Persistent memory. CLI control. But the real unlock is the compounding loop: You give Hermes a task. It records every tool call, decision, and result. Then it converts successful workflows into reusable skills automatically. A Hermes setup running for 3 months becomes fundamentally smarter than a fresh install. That’s the big idea. One of the coolest parts: You literally watch the agent evolve in real time from a blank install into a personalized AI operator. Instead of watching Netflix today, spend 28 mins with this. Follow Dami-Defi for more AI systems, agent workflows, and infrastructure alpha.

MOST AI AGENTS RESET TO ZERO EVERY TIME YOU OPEN A NEW SESSION. Hermes Agent was built to do the opposite. Every task compounds. Every workflow becomes reusable. Every session teaches the next one. That is the core thesis behind Hermes, and it completely changes how AI agents work. Unlike most AI agents built by software tool companies, Hermes was created by the researchers training the Hermes model family itself. Meaning: The same system used internally to generate training data is now open source and available to everyone. One install gives you access to: Claude. GPT. Grok. Local models via Ollama. Telegram, Discord, Slack, iMessage integrations. Custom skills. Persistent memory. CLI control. But the real unlock is the compounding loop: You give Hermes a task. It records every tool call, decision, and result. Then it converts successful workflows into reusable skills automatically. A Hermes setup running for 3 months becomes fundamentally smarter than a fresh install. That’s the big idea. One of the coolest parts: You literally watch the agent evolve in real time from a blank install into a personalized AI operator. Instead of watching Netflix today, spend 28 mins with this. Follow Dami-Defi for more AI systems, agent workflows, and infrastructure alpha.

Dami-Defi

11,685 views • 4 months ago

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.

DegenCalls

20,124 views • 2 months ago