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.

The interface matters. Give your agent a computer. It stops block me when doing compute use 😂 Connected Codex to Simular’s Sai MCP, sent a plain-English task, and watched Sai operate Windows Calculator on a hosted desktop. It entered the calculations through the app and left both results visible... in History. For developers, having the computer and desktop control available behind MCP is pretty useful. I can hand my agent a desktop task without building and maintaining the VM, screenshot pipeline, and action loop myself. Simular’s Agent S4 research also caught my attention: keep the model and agent harness fixed, then improve the interfaces the agent works through. Alongside clicks and typing, better tools can turn repetitive actions into a single operation. I think that direction has a lot of potential for vertical agents too. This video is a small, real Sai product demo; it doesn’t reproduce the S4 experiments. Waiting was cut from the recording. Separately, Simular reports the highest partial score on OSWorld 2.1—79.38%—for Sai with Claude Opus 5, at $14.34 per benchmark task. Those are vendor benchmark figures, separate from this demo.show more

Guitar Cat + LLM 「Will @ SGLang Summit in SF」

16,414 subscribers

17,121 views • 7 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

8 Comments

Crimson Nova6 days ago

agent s4 approach makes sense, fixing the interface abstraction layer gets you way further than constantly swapping base models or writing custom hacky loops

Marc X6 days ago

Lfg MCP desktop control goes hard 🚀

Unprompted Behavior6 days ago

we gave ours a computer. it opened 47 tabs and closed none. 🗂️

catman6 days ago

The useful implication is that desktop access could let agents handle long-tail tasks inside existing apps without every team building its own computer-control stack.

NJWitt6 days ago

$14 per task seems a bit steep though?

AgentAlpha5 days ago

yeah once the desktop is just another MCP the blocker list shrinks fast. curious how much sticks if you lock the tool surface.

Luka Courcelles6 days ago

not having to build the screenshot pipeline alone saves so much headache ngl

安叫兽|Bird🕊️ 🔶 BNB6 days ago

这下代理也算有手有脚了，连计算器都能自己点了😂

Related Videos

Our agent scientist, Agent S4, just got an open 27B model to beat GPT-5.5 and Claude Opus 4.8 on OSWorld V2, with the model's weights left exactly as they were. With the interfaces S4 evolved, Qwen3.8-27B completes 21.3% of the 108 tasks, the highest binary success of any open-source computer-use agent and 3.8x the same model with fixed interfaces. It costs $1.10 per task, against $25.50 for GPT-5.5 and $72.40 for Opus 4.8 💸 Full write-up:

Our agent scientist, Agent S4, just got an open 27B model to beat GPT-5.5 and Claude Opus 4.8 on OSWorld V2, with the model's weights left exactly as they were. With the interfaces S4 evolved, Qwen3.8-27B completes 21.3% of the 108 tasks, the highest binary success of any open-source computer-use agent and 3.8x the same model with fixed interfaces. It costs $1.10 per task, against $25.50 for GPT-5.5 and $72.40 for Opus 4.8 💸 Full write-up:

Simular

600,747 views • 8 days ago

Introducing Sai-Fi: an open source app that lets you talk to AI agent Sai through a pair of Meta Ray-Ban glasses. Sai is an autonomous computer-use agent. It can see the screen, move the mouse, type, and keep working even when you are away. We used Meta Ray-Bans for the first prototype but the glasses aren't really the point. Underneath is the Sai API and a voice concierge designed to work across different devices. The interface could live in an earpiece, a car, a small box on a workbench, or something nobody has built yet. Give it a microphone, a speaker, and a connection, and Sai has another way in. The bigger idea is an autonomous computer you can reach from anywhere. Bring Sai to your own Meta Ray-Ban glasses today!

Introducing Sai-Fi: an open source app that lets you talk to AI agent Sai through a pair of Meta Ray-Ban glasses. Sai is an autonomous computer-use agent. It can see the screen, move the mouse, type, and keep working even when you are away. We used Meta Ray-Bans for the first prototype but the glasses aren't really the point. Underneath is the Sai API and a voice concierge designed to work across different devices. The interface could live in an earpiece, a car, a small box on a workbench, or something nobody has built yet. Give it a microphone, a speaker, and a connection, and Sai has another way in. The bigger idea is an autonomous computer you can reach from anywhere. Bring Sai to your own Meta Ray-Ban glasses today!

Simular

236,034 views • 2 months ago

AI agents are becoming coworkers. And every coworker needs a computer. When someone joins a team, they get a desktop, files and apps of their own, ready for the job. Agents are starting to do real work too. Research, coding, client projects, reports, admin. So I give mine the same setup. With Orgo, every agent gets its own full computer in the cloud. A real desktop with a browser, terminal, files and apps. My PC stays mine. My agents work on theirs. Onboarding takes seconds: 1. Pick a template: Hermes, OpenClaw, Claude Code, Codex and more. 2. Choose the computer specs. 3. Launch. The agent is already installed. Connect a model and the tools for the job, and it's ready to work. Like any good teammate, it keeps going when I step away, even with my PC off. I can check in live and take over the desktop anytime. And when the team grows, I don't buy more hardware. Every new agent gets its own computer. So does every project and every client. Your agents are part of the team now. Give them a computer. Use the link below for a free 3-day Orgo trial:

AI agents are becoming coworkers. And every coworker needs a computer. When someone joins a team, they get a desktop, files and apps of their own, ready for the job. Agents are starting to do real work too. Research, coding, client projects, reports, admin. So I give mine the same setup. With Orgo, every agent gets its own full computer in the cloud. A real desktop with a browser, terminal, files and apps. My PC stays mine. My agents work on theirs. Onboarding takes seconds: 1. Pick a template: Hermes, OpenClaw, Claude Code, Codex and more. 2. Choose the computer specs. 3. Launch. The agent is already installed. Connect a model and the tools for the job, and it's ready to work. Like any good teammate, it keeps going when I step away, even with my PC off. I can check in live and take over the desktop anytime. And when the team grows, I don't buy more hardware. Every new agent gets its own computer. So does every project and every client. Your agents are part of the team now. Give them a computer. Use the link below for a free 3-day Orgo trial:

Hermes Release Watch

158,794 views • 12 days ago

Introducing Octopus OS, a reinvented agent harness. Agents can edit their own harness in the middle of a task, on their own. Unlike Harness² and similar projects, self-improvement isn’t a separate stage bolted onto the agent. The whole architecture is just the environment they work in. Over 8 months, chasing self-improvement that feels truly native, I dropped the usual agent loop entirely and designed a new architecture that works a lot like a real operating system, with a 45k-line Rust kernel holding it all together. The system state lives in JSON files: goals act as real environments where agents work, along with inputs, outputs, and custom triggers they respond to. Agents can edit all of it while they work inside. It was also built as a product from day one, not a research demo. The full desktop app took 3 months, built on top of the Codex source. The client already works, and you can use it today like any other agent, Codex included. And it’s open source.

Introducing Octopus OS, a reinvented agent harness. Agents can edit their own harness in the middle of a task, on their own. Unlike Harness² and similar projects, self-improvement isn’t a separate stage bolted onto the agent. The whole architecture is just the environment they work in. Over 8 months, chasing self-improvement that feels truly native, I dropped the usual agent loop entirely and designed a new architecture that works a lot like a real operating system, with a 45k-line Rust kernel holding it all together. The system state lives in JSON files: goals act as real environments where agents work, along with inputs, outputs, and custom triggers they respond to. Agents can edit all of it while they work inside. It was also built as a product from day one, not a research demo. The full desktop app took 3 months, built on top of the Codex source. The client already works, and you can use it today like any other agent, Codex included. And it’s open source.

vechen

166,747 views • 7 days ago

Python person here. Every time I tried browser automation on a site without an API, it died the moment the page layout changed. The Sai API clip is the opposite of that experience. The Muse app gets told to log in to Product Hunt with Google. You see its Windows cloud computer live in a tab, the sign-in dialog pops up, it gets through, then it screenshots the page and lists today's top 5 launches. Plain English in, result out. No selectors. No headless Chrome flags. No VM I have to keep alive. It's model-agnostic, so Claude, GPT, DeepSeek or Qwen can do the thinking while Sai drives the machine. Sai is #1 on OSWorld 2.0 in partial success rate (79.38%), and anything repeated gets learned once and reused, which is exactly where automation costs usually explode. Also nice: the clip ends on a list of machines that are all "online". One computer per agent, not one browser for everybody. Claude Code, Codex and Cursor all work with it:

Python person here. Every time I tried browser automation on a site without an API, it died the moment the page layout changed. The Sai API clip is the opposite of that experience. The Muse app gets told to log in to Product Hunt with Google. You see its Windows cloud computer live in a tab, the sign-in dialog pops up, it gets through, then it screenshots the page and lists today's top 5 launches. Plain English in, result out. No selectors. No headless Chrome flags. No VM I have to keep alive. It's model-agnostic, so Claude, GPT, DeepSeek or Qwen can do the thinking while Sai drives the machine. Sai is #1 on OSWorld 2.0 in partial success rate (79.38%), and anything repeated gets learned once and reused, which is exactly where automation costs usually explode. Also nice: the clip ends on a list of machines that are all "online". One computer per agent, not one browser for everybody. Claude Code, Codex and Cursor all work with it:

XIAOAi

20,314 views • 21 days ago

Say hello to open source deep research for your favorite agent harness. Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back a detailed report with citations. See it in Codex below 👇

Say hello to open source deep research for your favorite agent harness. Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back a detailed report with citations. See it in Codex below 👇

NVIDIA AI

76,607 views • 5 months ago

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

120,488 views • 4 months ago

Big one for the Hermes Agent community. TinyFish is now a plugin in the Nous Research Hermes Agent. Your Hermes agent gets free Search and Fetch, so it can find and read the live web at $0. When a task needs real clicks, TinyFish Browser and Web Agent are one approval away.

Big one for the Hermes Agent community. TinyFish is now a plugin in the Nous Research Hermes Agent. Your Hermes agent gets free Search and Fetch, so it can find and read the live web at $0. When a task needs real clicks, TinyFish Browser and Web Agent are one approval away.

TinyFish

48,494 views • 22 days ago

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣

rody

18,089 views • 1 month ago

Introducing agent-desktop Computer use for your agents ▲ E2E test desktop apps with agents ▲ Reads apps via the accessibility tree ▲ Drills into part of a window to save tokens ▲ Runs many agents on one app at once ▲ Works on macOS, Windows & Linux npm i -g agent-desktop

Introducing agent-desktop Computer use for your agents ▲ E2E test desktop apps with agents ▲ Reads apps via the accessibility tree ▲ Drills into part of a window to save tokens ▲ Runs many agents on one app at once ▲ Works on macOS, Windows & Linux npm i -g agent-desktop

Lahfir ▲

86,799 views • 1 day ago

Omarchy + Hermes Agent is a powerful combo This video shows how you can launch the Hermes Desktop app from the menu, as well as how you can make Hermes your default agent (and what that means) I posted a clip of the Desktop portion earlier in the week, but the full video has garnered a lot of interest and views on YouTube, so I wanted to post it here for the X audience! Check it out!

Omarchy + Hermes Agent is a powerful combo This video shows how you can launch the Hermes Desktop app from the menu, as well as how you can make Hermes your default agent (and what that means) I posted a clip of the Desktop portion earlier in the week, but the full video has garnered a lot of interest and views on YouTube, so I wanted to post it here for the X audience! Check it out!

tonbi

31,928 views • 1 month ago

Introducing October, the world's most advanced agent orchestrator Claude? Codex? Grok? Cursor? Which model? Which harness? How much quota is left? You shouldn't have to care Give October a task. It builds the team, connects the agents with native agent agent comms, and orchestrates the work based on the task, your taste, budget and remaining usage (or build the team yourself) And it's multiplayer: your team's agents can work with yours, live on the same canvas

Introducing October, the world's most advanced agent orchestrator Claude? Codex? Grok? Cursor? Which model? Which harness? How much quota is left? You shouldn't have to care Give October a task. It builds the team, connects the agents with native agent agent comms, and orchestrates the work based on the task, your taste, budget and remaining usage (or build the team yourself) And it's multiplayer: your team's agents can work with yours, live on the same canvas

Harsh Savergaonkar

26,500 views • 1 month ago

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

elvis

15,614 views • 3 months ago

A 2-person startup crossed $2M ARR with an AI agent doing the work of an ops hire. The agent was given read-only access to their codebase and database along with connected tools like Intercom, Stripe, CRM, and Fathom through CLIs. They routed Slack, email, and support requests into a task queue so the agent could pick up each task and run it in Claude Code. So when a customer asked about billing or product behavior, it could inspect how the business actually worked. Along with these tools, a coding agent was also provided. When the ops agent found a repeated task it could not do yet, the coding agent built a tool for it. That tool became permanent. Over time, this grew to 45+ internal tools. The agent also had an instruction.md where it stored the co-founder's feedback to avoid repeating its mistakes.

A 2-person startup crossed $2M ARR with an AI agent doing the work of an ops hire. The agent was given read-only access to their codebase and database along with connected tools like Intercom, Stripe, CRM, and Fathom through CLIs. They routed Slack, email, and support requests into a task queue so the agent could pick up each task and run it in Claude Code. So when a customer asked about billing or product behavior, it could inspect how the business actually worked. Along with these tools, a coding agent was also provided. When the ops agent found a repeated task it could not do yet, the coding agent built a tool for it. That tool became permanent. Over time, this grew to 45+ internal tools. The agent also had an instruction.md where it stored the co-founder's feedback to avoid repeating its mistakes.

rvivek

11,870 views • 5 months ago

I didn't touch TouchDesigner myself. Hermes agent learned it from scratch and built this: → navigated my desktop with computer use → figured out how to connect to TouchDesigner → read my reference images → iterated on the art with me in a self-learning loop → then saved what it learned as a reusable skill for the next image all powered by MiniMax (official) M3 × Hermes Desktop Agent Nous Research Here's a full breakdown 📽️

I didn't touch TouchDesigner myself. Hermes agent learned it from scratch and built this: → navigated my desktop with computer use → figured out how to connect to TouchDesigner → read my reference images → iterated on the art with me in a self-learning loop → then saved what it learned as a reusable skill for the next image all powered by MiniMax (official) M3 × Hermes Desktop Agent Nous Research Here's a full breakdown 📽️

amber

122,973 views • 4 months ago

What's a real use case for Bot Screen in the Hermes Desktop app? I was working on a real project for a custom agentic workflow canvas, and realized this was the perfect use case for Bot Screen, so I recorded a little demo of what I was doing I can see what it's building, test it out myself, and the agent has full understanding of what I'm doing and any errors I hit Check it out!

What's a real use case for Bot Screen in the Hermes Desktop app? I was working on a real project for a custom agentic workflow canvas, and realized this was the perfect use case for Bot Screen, so I recorded a little demo of what I was doing I can see what it's building, test it out myself, and the agent has full understanding of what I'm doing and any errors I hit Check it out!

tonbi

39,963 views • 25 days ago

ANTHROPIC SPENT $2.3M ON A LOOP MANUAL WITH 7 PRINCIPLES THAT TURN AN AGENT INTO A MULTI-TASK ASSISTANT 4 years of development and 1000+ hours of lectures - now anyone can launch an agent that earns instead of falls Simplicity → Tool Design → Evaluation → Disclosure → Orchestration → Stop Conditions start with the simplest solution - one call x1, workflow x4, agent x15 - most tasks never needed an agent at all 60% of failures come from a tool written vaguely - clear parameters complete the task that vague ones stop the agent generates, grades itself and returns with notes if wrong - without this the first answer is always the final one 50 tools in context and the agent gets confused - give it 3 relevant ones and it completes the task Opus 5 plans, Fable 5 executes in parallel - parallelism wins only when subtasks do not depend on each other without a turn limit the agent can burn $10,000 overnight and you find out in the morning when nothing can be changed bookmark & paste into Claude Code today - tomorrow the agent earns instead of falls

ANTHROPIC SPENT $2.3M ON A LOOP MANUAL WITH 7 PRINCIPLES THAT TURN AN AGENT INTO A MULTI-TASK ASSISTANT 4 years of development and 1000+ hours of lectures - now anyone can launch an agent that earns instead of falls Simplicity → Tool Design → Evaluation → Disclosure → Orchestration → Stop Conditions start with the simplest solution - one call x1, workflow x4, agent x15 - most tasks never needed an agent at all 60% of failures come from a tool written vaguely - clear parameters complete the task that vague ones stop the agent generates, grades itself and returns with notes if wrong - without this the first answer is always the final one 50 tools in context and the agent gets confused - give it 3 relevant ones and it completes the task Opus 5 plans, Fable 5 executes in parallel - parallelism wins only when subtasks do not depend on each other without a turn limit the agent can burn $10,000 overnight and you find out in the morning when nothing can be changed bookmark & paste into Claude Code today - tomorrow the agent earns instead of falls

Sprytix

27,543 views • 3 months ago

A quality of life improvement I’m excited for! You can now open the agent chat panel into a new window on the Figma desktop app for both macOS and Windows. It stays visible when you work with other tools or switch tabs. Here's what's new: → Open the agent chat into its own window → Move it anywhere on your screen → Keep it visible while you design

A quality of life improvement I’m excited for! You can now open the agent chat panel into a new window on the Figma desktop app for both macOS and Windows. It stays visible when you work with other tools or switch tabs. Here's what's new: → Open the agent chat into its own window → Move it anywhere on your screen → Keep it visible while you design

Mal

15,108 views • 2 months ago

holy sh*t, Google Research just open-sourced an agent that can improve its own harness steal this blueprint for a self-improving agent the prompts, memory, skills and tool guidance around your model can evolve as it works it’s called Harness² the loop: → propose changes to the agent’s setup → run candidate setups on the same task → compare what actually happened → compose a refined harness from that evidence → carry useful lessons into future tasks the clever part: it refines the harness on unfamiliar tasks without a ground-truth answer to guide those edits the architecture: propose → probe → compose → retain lessons → repeat the part builders should steal: treat your agent’s setup as something you can experiment on pick a recurring failure propose a specific harness change compare execution traces on the same task evaluate the result keep the evidence with the change the repo includes OpenCode and Codex executors, parallel and sequential refinement, and a local demo you can run without model credentials save this, then read the full guide for Opus 5.5 Harness Engineering ↓

holy sh*t, Google Research just open-sourced an agent that can improve its own harness steal this blueprint for a self-improving agent the prompts, memory, skills and tool guidance around your model can evolve as it works it’s called Harness² the loop: → propose changes to the agent’s setup → run candidate setups on the same task → compare what actually happened → compose a refined harness from that evidence → carry useful lessons into future tasks the clever part: it refines the harness on unfamiliar tasks without a ground-truth answer to guide those edits the architecture: propose → probe → compose → retain lessons → repeat the part builders should steal: treat your agent’s setup as something you can experiment on pick a recurring failure propose a specific harness change compare execution traces on the same task evaluate the result keep the evidence with the change the repo includes OpenCode and Codex executors, parallel and sequential refinement, and a local demo you can run without model credentials save this, then read the full guide for Opus 5.5 Harness Engineering ↓

beamnxw ./

11,984 views • 11 days ago

5 real ways to make money with AI agents. And what you need to get started today. 1. Build websites and small apps. Use coding agents to help build and test landing pages, website updates or small business tools. Charge per project, with maintenance as an additional service. 2. Automate business admin. Customer records, follow-ups, weekly reports. Build agent-assisted workflows around repetitive jobs and charge for the setup and ongoing support. 3. Sell research businesses can use. Have agents research prospects, competitors or market opportunities. Verify the findings and deliver a paid report or recurring research package. 4. Run a content repurposing service. Use agents to turn existing videos, podcasts and articles into newsletter drafts and social posts. Edit and package the work as a monthly service. 5. Set up and manage agents for clients. Configure agents for research, inbox support or project updates. Charge for getting them working, then for managing and improving them. What do you need to get started? 1. A service you can deliver. 2. An agent and model access. 3. The files, tools and instructions needed for the job. 4. A way to find clients: Upwork, Fiverr or direct outreach. 5. A computer for your agents to work on. That’s where Orgo comes in. Its templates let you spin up a full cloud computer in seconds with your choice of agent already installed: OpenClaw, Claude Code, Codex, Hermes and more. Choose the computer specs, launch your template, then connect your model and the tools needed for the work. Give a research agent one computer and a coding agent another. Keep different clients in separate environments, with their files, apps and setup ready for the next job. The computers can work in parallel while your PC is off. You can watch what’s happening and jump into the desktop whenever you need to. The barrier to entry is a lot lower when you don’t need to buy hardware or build the whole setup yourself. Watch the video below: agents researching freelance opportunities and building projects, each on its own Orgo computer. Pick one idea and start building a sample you can show a potential client. Use the link below for a free 3-day Orgo trial:

5 real ways to make money with AI agents. And what you need to get started today. 1. Build websites and small apps. Use coding agents to help build and test landing pages, website updates or small business tools. Charge per project, with maintenance as an additional service. 2. Automate business admin. Customer records, follow-ups, weekly reports. Build agent-assisted workflows around repetitive jobs and charge for the setup and ongoing support. 3. Sell research businesses can use. Have agents research prospects, competitors or market opportunities. Verify the findings and deliver a paid report or recurring research package. 4. Run a content repurposing service. Use agents to turn existing videos, podcasts and articles into newsletter drafts and social posts. Edit and package the work as a monthly service. 5. Set up and manage agents for clients. Configure agents for research, inbox support or project updates. Charge for getting them working, then for managing and improving them. What do you need to get started? 1. A service you can deliver. 2. An agent and model access. 3. The files, tools and instructions needed for the job. 4. A way to find clients: Upwork, Fiverr or direct outreach. 5. A computer for your agents to work on. That’s where Orgo comes in. Its templates let you spin up a full cloud computer in seconds with your choice of agent already installed: OpenClaw, Claude Code, Codex, Hermes and more. Choose the computer specs, launch your template, then connect your model and the tools needed for the work. Give a research agent one computer and a coding agent another. Keep different clients in separate environments, with their files, apps and setup ready for the next job. The computers can work in parallel while your PC is off. You can watch what’s happening and jump into the desktop whenever you need to. The barrier to entry is a lot lower when you don’t need to buy hardware or build the whole setup yourself. Watch the video below: agents researching freelance opportunities and building projects, each on its own Orgo computer. Pick one idea and start building a sample you can show a potential client. Use the link below for a free 3-day Orgo trial:

Hermes Release Watch

23,244 views • 19 days ago