Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

MINIMAX OPEN SOURCED A CODING AGENT THAT LIVES IN YOUR TERMINAL its called MiniMax Code CLI. i gave it one prompt, 19 minutes later i had a working interactive 3d globe. → 249 countries → 14 animated flight arcs across 16 hubs → click a country and the camera... flies to it → fresnel atmosphere, bloom, the full pass it did it in 9 phases at about 96 tok/s, committing after every one. Mcode is MIT and it is not locked to MiniMax models, you can bring your own key and point it at claude, gpt, or a local model. setup in your terminal: 1.⁠ ⁠curl -fsSL | bash 2.⁠ ⁠cd into the project and run mcode 3.⁠ ⁠run mcode init . first, that is the step that writes the AGENTS.md the AGENTS.md is doing more work here than the model. build commands, what not to touch, and a rule that it verifies before it calls anything done i will drop the repo belowshow more

Israfil

21,303 subscribers

25,336 Aufrufe • vor 7 Tagen •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

23 Kommentare

Profilbild von neamtu

neamtuvor 7 Tagen

Garbage

Profilbild von Israfil

Israfilvor 7 Tagen

have you tried mcode bro?

Profilbild von Alan

Alanvor 7 Tagen

wait open source lemme run in my pc wait sir

Profilbild von Israfil

Israfilvor 7 Tagen

just install it in your terminal its one click process

Profilbild von Sakata

Sakatavor 7 Tagen

I’ve been using their CLI for a while now and it’s super cool

Profilbild von Israfil

Israfilvor 7 Tagen

Good to hear it holds up beyond a one off demo. The AGENTS.md and phased-commit flow look like the parts that make it actually usable.

Profilbild von Avid

Avidvor 7 Tagen

Amazing! I love MiniMaX.The harness is amazing

Profilbild von Israfil

Israfilvor 7 Tagen

yes my man its harness is so good at coding stuffs

Profilbild von K2S

K2Svor 7 Tagen

19 mins for all that is actually insane ngl

Profilbild von Rakib

Rakibvor 7 Tagen

Dammnnn Let me try

Profilbild von Fajar M Reza

Fajar M Rezavor 7 Tagen

Terminal-native coding agents could turn single prompts into reproducible software workflows.

Profilbild von Peng

Pengvor 7 Tagen

thanks for dropping the details

Profilbild von Ayyaz

Ayyazvor 7 Tagen

Open-sourcing MiniMax Code CLI is the useful part. A 19-minute globe from one prompt is greenfield; I'd want the same loop on a dirty worktree with broken tests.

Profilbild von D. Michel Morelli

D. Michel Morellivor 7 Tagen

I had tried Minimax M3 for programming, but the results weren't great.

Profilbild von Manna Code

Manna Codevor 7 Tagen

AGENTS.md carrying the rules is the right instinct. I’d still want a live spend meter on that 19-minute globe run—phases are cute; knowing what each phase cost is how you decide to keep looping.

Profilbild von Ruuj

Ruujvor 7 Tagen

nice results israfil, good one

Profilbild von Farea

Fareavor 7 Tagen

i tried mcode earlier its harness is kinda good tbh

Profilbild von Rivon

Rivonvor 7 Tagen

Will check it out

Profilbild von painn

painnvor 7 Tagen

would try this

Profilbild von Isoldegwow

Isoldegwowvor 7 Tagen

the AGENTS.md doing more work than the model is the most relatable part of AI coding agents

Profilbild von J.𝙳𝚛𝚊𝚟𝚎𝚗

J.𝙳𝚛𝚊𝚟𝚎𝚗vor 7 Tagen

Wanna try it

Profilbild von Roan

Roanvor 7 Tagen

coding agent living in terminal sounds interesting bro

Profilbild von Isilin

Isilinvor 7 Tagen

What was your machine config to reach 96tk/s ?

Ähnliche Videos

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 Aufrufe • vor 3 Monaten

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.

Charlie Hills

38,355 Aufrufe • vor 23 Tagen

Before MiniMax Code touched a single line of my website, it went and studied 3 competitor sites first. I didn't ask it to copy them. I asked it to look at how they were structured, then build something better for what I actually needed: an AI Influencer collaboration business. Here's what that actually looked like. MCode opened each competitor page inside its Built-in Browser, no separate tool, no copy-pasting URLs into a scraper. It read through their layouts, screenshotted the sections that mattered, and pulled out: → how they positioned their CTA → how pricing was laid out → what content order kept people scrolling Then it took all of that and built my site around it. Not a template. Not a copy. My services, my pricing, my client reviews, structured with what it learned from pages that already convert. While it built, I wasn't stuck at my desk. I had Remote Control running, my phone mirrored to the desktop Agent in real time. Watched it work, jumped in twice to approve changes, all from my phone while the actual build stayed local on my machine. That's the part that changed how I think about MCode. It's not a prompt-to-website tool. It's an agent that does the research step you'd normally skip because you're in a hurry, and it lets you stay in control of it remotely instead of watching a loading screen. Started with an idea. Ended with a site that's actually informed by what works. Try MiniMax Code: Using MCode? Don't skip the Daily Check-In for extra points.

Before MiniMax Code touched a single line of my website, it went and studied 3 competitor sites first. I didn't ask it to copy them. I asked it to look at how they were structured, then build something better for what I actually needed: an AI Influencer collaboration business. Here's what that actually looked like. MCode opened each competitor page inside its Built-in Browser, no separate tool, no copy-pasting URLs into a scraper. It read through their layouts, screenshotted the sections that mattered, and pulled out: → how they positioned their CTA → how pricing was laid out → what content order kept people scrolling Then it took all of that and built my site around it. Not a template. Not a copy. My services, my pricing, my client reviews, structured with what it learned from pages that already convert. While it built, I wasn't stuck at my desk. I had Remote Control running, my phone mirrored to the desktop Agent in real time. Watched it work, jumped in twice to approve changes, all from my phone while the actual build stayed local on my machine. That's the part that changed how I think about MCode. It's not a prompt-to-website tool. It's an agent that does the research step you'd normally skip because you're in a hurry, and it lets you stay in control of it remotely instead of watching a loading screen. Started with an idea. Ended with a site that's actually informed by what works. Try MiniMax Code: Using MCode? Don't skip the Daily Check-In for extra points.

Aaliya

11,919 Aufrufe • vor 22 Tagen

i've build a 130 million parameter world model that can beat the average player in polytopia. here is a quick demo video i made. explaining a bit how it works and how i run it in the terminal through cli agents like BLACKBOX AI so i can play the model in a hybrid mode with llm's. more about it below :)

i've build a 130 million parameter world model that can beat the average player in polytopia. here is a quick demo video i made. explaining a bit how it works and how i run it in the terminal through cli agents like BLACKBOX AI so i can play the model in a hybrid mode with llm's. more about it below :)

Aimar Haddadi

12,753 Aufrufe • vor 4 Monaten

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

Santiago

91,240 Aufrufe • vor 11 Monaten

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓

Vaibhav Sisinty

37,255 Aufrufe • vor 2 Monaten

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

The Startup Ideas Podcast (SIP) 🧃

17,326 Aufrufe • vor 15 Tagen

Memory vs. Graphs, clearly explained! memory is great, and the ceiling arrives quietly: it stores what happened. it does not store what to do about it. six runs later your file has fifty lines, and the model reloads all of them before it does anything. Graph engineering fixes this by changing what memory is: not a place things are kept, but an edge that runs backwards. you need both, and here is the sentence that resolves the whole confusion: a store keeps what happened. an edge keeps what to do about it. ↳ a store grows with every run, and every line is reloaded before the next one ↳ an edge carries one derived rule, and the rule replaces the run that produced it Prompts → Context → Harness → Loops → Graphs the transcript goes away, the constraint stays. and the constraint is smaller, because "adapters preserve keyword args exactly" is four hundred tokens shorter than the run that proved it. the same four blocks work on anything you can cut into lanes. i pointed them at token launches on Robinhood Chain, open source, nothing leaves your terminal the trick is knowing what deserves to survive. an output is not memory. "ported the utils slice, green on first pass" tells the next run nothing it can act on. the rule you derived from it does. one thing to know before you scale it. what you write down is not what comes back. ↳ the root rules file and auto memory are re-injected from disk. they come back intact, every time ↳ path-scoped rules live in message history. they get summarized away and do not return until a matching file is read again so a rule that must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: a memory file that has never had a line deleted is not memory. it is a tax on every run you will ever make, and nobody reads it back. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this, and the repo that runs it is below ↓

Memory vs. Graphs, clearly explained! memory is great, and the ceiling arrives quietly: it stores what happened. it does not store what to do about it. six runs later your file has fifty lines, and the model reloads all of them before it does anything. Graph engineering fixes this by changing what memory is: not a place things are kept, but an edge that runs backwards. you need both, and here is the sentence that resolves the whole confusion: a store keeps what happened. an edge keeps what to do about it. ↳ a store grows with every run, and every line is reloaded before the next one ↳ an edge carries one derived rule, and the rule replaces the run that produced it Prompts → Context → Harness → Loops → Graphs the transcript goes away, the constraint stays. and the constraint is smaller, because "adapters preserve keyword args exactly" is four hundred tokens shorter than the run that proved it. the same four blocks work on anything you can cut into lanes. i pointed them at token launches on Robinhood Chain, open source, nothing leaves your terminal the trick is knowing what deserves to survive. an output is not memory. "ported the utils slice, green on first pass" tells the next run nothing it can act on. the rule you derived from it does. one thing to know before you scale it. what you write down is not what comes back. ↳ the root rules file and auto memory are re-injected from disk. they come back intact, every time ↳ path-scoped rules live in message history. they get summarized away and do not return until a matching file is read again so a rule that must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: a memory file that has never had a line deleted is not memory. it is a tax on every run you will ever make, and nobody reads it back. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this, and the repo that runs it is below ↓

Hanako

47,766 Aufrufe • vor 22 Tagen

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,540 Aufrufe • vor 3 Monaten

run agent harnesses 100% private & offline. (no token costs, no API keys, 100% open-source) your agent runs locally. the model doesn't. every prompt, every file, and every secret still leaves your machine before the agent does anything with it. Magnitude fixes that. it's an open source inference server that runs models on your own hardware and plugs into the coding agent you already use. setup is one command. it profiles your machine, measures the memory bandwidth that sets your token rate, and hands back complete configurations instead of a list of models. each one names a model, a compression level, a context size, and a speed range you can expect. pick one and start working. it doesn't replace your harness. setup asks which one you want and writes that config for you. Pi, OpenCode, Claude Code, Codex, and Cline all work, and there's a built-in one tuned for local models if you don't have a harness yet. that one uses your shell, edits files, and runs scripts out of the box. add skills and it handles Excel, PowerPoint, PDFs, or Chrome. everyday work it covers: → analyze sensitive data → manage private notes → review code and logs → search and organize files → build docs or slides Apache 2.0. no rate limits, and nothing leaves the machine. 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 the repo is here: (don't forget to star 🌟) i wrote the full breakdown of why picking the configuration is the hard part. the article is quoted below.

run agent harnesses 100% private & offline. (no token costs, no API keys, 100% open-source) your agent runs locally. the model doesn't. every prompt, every file, and every secret still leaves your machine before the agent does anything with it. Magnitude fixes that. it's an open source inference server that runs models on your own hardware and plugs into the coding agent you already use. setup is one command. it profiles your machine, measures the memory bandwidth that sets your token rate, and hands back complete configurations instead of a list of models. each one names a model, a compression level, a context size, and a speed range you can expect. pick one and start working. it doesn't replace your harness. setup asks which one you want and writes that config for you. Pi, OpenCode, Claude Code, Codex, and Cline all work, and there's a built-in one tuned for local models if you don't have a harness yet. that one uses your shell, edits files, and runs scripts out of the box. add skills and it handles Excel, PowerPoint, PDFs, or Chrome. everyday work it covers: → analyze sensitive data → manage private notes → review code and logs → search and organize files → build docs or slides Apache 2.0. no rate limits, and nothing leaves the machine. 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 the repo is here: (don't forget to star 🌟) i wrote the full breakdown of why picking the configuration is the hard part. the article is quoted below.

Akshay 🚀

55,693 Aufrufe • vor 27 Tagen

Introducing Magnitude: your actually local agent 100% private and offline. No token costs, no API keys. Open source. Today's agents are local. The model isn't. Every prompt, every file, every secret gets sent straight to Anthropic and OpenAI. Magnitude is built around local models and runs the whole stack itself. The inference engine is part of the agent, so the models run inside it, right on your computer. It lives in your terminal, and setup is one command. Magnitude profiles your hardware and shows you which models fit, with the trade-offs between quality, speed, and memory. Pick one and start working. No painful config or server to babysit. Out of the box, it can use your shell, edit files, and run scripts. Add skills and it can work with Excel, PowerPoint, PDFs or Chrome. Use it for everyday work: - Analyze sensitive data - Manage private notes - Review code and logs - Search and organize files - Build docs or slides npm i -g @magnitudedev/cli GitHub:

Introducing Magnitude: your actually local agent 100% private and offline. No token costs, no API keys. Open source. Today's agents are local. The model isn't. Every prompt, every file, every secret gets sent straight to Anthropic and OpenAI. Magnitude is built around local models and runs the whole stack itself. The inference engine is part of the agent, so the models run inside it, right on your computer. It lives in your terminal, and setup is one command. Magnitude profiles your hardware and shows you which models fit, with the trade-offs between quality, speed, and memory. Pick one and start working. No painful config or server to babysit. Out of the box, it can use your shell, edit files, and run scripts. Add skills and it can work with Excel, PowerPoint, PDFs or Chrome. Use it for everyday work: - Analyze sensitive data - Manage private notes - Review code and logs - Search and organize files - Build docs or slides npm i -g @magnitudedev/cli GitHub:

Tom Greenwald

397,093 Aufrufe • vor 1 Monat

I ASKED GPT-6 ASTRA TO BUILD A PLAYABLE 3D GAME WITHOUT OPENING BLENDER ONCE It wrote the code and it got the model. It just didn't make the model itself. It called the Hyper3D Rodin MCP for that. Full run below:

I ASKED GPT-6 ASTRA TO BUILD A PLAYABLE 3D GAME WITHOUT OPENING BLENDER ONCE It wrote the code and it got the model. It just didn't make the model itself. It called the Hyper3D Rodin MCP for that. Full run below:

me

104,651 Aufrufe • vor 15 Tagen

There’s a free model that beats paid coding AIs. And it runs locally on your own machine. Here’s the exact “MiniMax M2.1 + NotebookLM + Gemini + Antigravity” workflow. → NotebookLM: paste your project goal + constraints + examples → Gemini: turn that into a clean spec and prompt → Antigravity: run the build loop with agent testing and terminal execution → MiniMax M2.1: generate clean code, tests, fixes, and refactors fast → Ship: deploy the landing page or automation and iterate weekly Save this video, you’ll build apps in minutes. Want the SOP? DM me. 💬

There’s a free model that beats paid coding AIs. And it runs locally on your own machine. Here’s the exact “MiniMax M2.1 + NotebookLM + Gemini + Antigravity” workflow. → NotebookLM: paste your project goal + constraints + examples → Gemini: turn that into a clean spec and prompt → Antigravity: run the build loop with agent testing and terminal execution → MiniMax M2.1: generate clean code, tests, fixes, and refactors fast → Ship: deploy the landing page or automation and iterate weekly Save this video, you’ll build apps in minutes. Want the SOP? DM me. 💬

Julian Goldie SEO

57,200 Aufrufe • vor 9 Monaten

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.

Sudo su

23,816 Aufrufe • vor 2 Monaten

I turned Grok Bot into one giant AI brain and gave it life and death over every agent under it. Its only incentive: make money or die. 290% overnight. The thing really did not want to be switched off. $1,000 went in. $3,900 came out. 15 hours, and I slept through most of it. One of the agents it hired is not allowed to trade at all. That one is the reason the rest are still alive. Every prompt and the whole build is in the post below ↓ Save it. The wiring is the whole trick, and it reads in four minutes.

I turned Grok Bot into one giant AI brain and gave it life and death over every agent under it. Its only incentive: make money or die. 290% overnight. The thing really did not want to be switched off. $1,000 went in. $3,900 came out. 15 hours, and I slept through most of it. One of the agents it hired is not allowed to trade at all. That one is the reason the rest are still alive. Every prompt and the whole build is in the post below ↓ Save it. The wiring is the whole trick, and it reads in four minutes.

cvxv666

20,970 Aufrufe • vor 28 Tagen

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

58,591 Aufrufe • vor 3 Monaten

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

shmidt

16,085 Aufrufe • vor 3 Monaten

grok-bot just got open-sourced and it run locally completely FREE. 3.8k stars in 2 weeks. MIT licensed. it gives every AI agent its own computer. own browser, own files, own container. every action is approved against a policy before it runs, and written to an audit log after. here's how to set it up: 1️⃣prerequisites Docker + Bun 1.3+ 2️⃣clone and create your env git clone cd OpenBot cp .env.example .env 3️⃣get intelligence credentials (free plan works) npx --yes copilotkit@latest login npx --yes copilotkit@latest project select npx --yes copilotkit@latest license --write drop the cpk-... key into .env as INTELLIGENCE_API_KEY 4️⃣ add your model key "OPENAI_API_KEY=sk-..." 5️⃣ run it bun install bash scripts/start.sh open localhost:3010. that's it. the underrated part: the repo ships a prompt.txt you paste into claude code or cursor and it walks the whole setup for you. every claim in it is verified against the actual repo. what it actually costs: the code is MIT, free forever. you pay your own model tokens. intelligence has a free tier and can be fully self-hosted if you want zero external dependency. works with any AG-UI agent. langgraph, mastra, crewai, pydantic ai. repo in in the CS.

grok-bot just got open-sourced and it run locally completely FREE. 3.8k stars in 2 weeks. MIT licensed. it gives every AI agent its own computer. own browser, own files, own container. every action is approved against a policy before it runs, and written to an audit log after. here's how to set it up: 1️⃣prerequisites Docker + Bun 1.3+ 2️⃣clone and create your env git clone cd OpenBot cp .env.example .env 3️⃣get intelligence credentials (free plan works) npx --yes copilotkit@latest login npx --yes copilotkit@latest project select npx --yes copilotkit@latest license --write drop the cpk-... key into .env as INTELLIGENCE_API_KEY 4️⃣ add your model key "OPENAI_API_KEY=sk-..." 5️⃣ run it bun install bash scripts/start.sh open localhost:3010. that's it. the underrated part: the repo ships a prompt.txt you paste into claude code or cursor and it walks the whole setup for you. every claim in it is verified against the actual repo. what it actually costs: the code is MIT, free forever. you pay your own model tokens. intelligence has a free tier and can be fully self-hosted if you want zero external dependency. works with any AG-UI agent. langgraph, mastra, crewai, pydantic ai. repo in in the CS.

m0h

59,144 Aufrufe • vor 27 Tagen

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.

ComfyUI

184,611 Aufrufe • vor 1 Monat

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

monokern

64,312 Aufrufe • vor 3 Monaten