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.

Hermes Agent can now /learn from anything: feed it directories of any source material (code, API docs, manuals, PDFs, configs) and it distills a verifiable reusable skill

Nous Research

277,575 subscribers

1,319,686 Aufrufe • vor 3 Monaten •via X (Twitter)

Bildung Nachrichten & Politik Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

38 Kommentare

Profilbild von Teknium 🪽

Teknium 🪽vor 3 Monaten

Time to get to school, Hermes

Profilbild von Nous Research

Nous Researchvor 3 Monaten

👩🏻‍💻

Profilbild von Nous Research

Nous Researchvor 3 Monaten

More on the /learn command:

Profilbild von Tyler Gibson

Tyler Gibsonvor 3 Monaten

my hermes after update.

Profilbild von Nous Research

Nous Researchvor 3 Monaten

Pretty much lol

Profilbild von Daniel Figueroa

Daniel Figueroavor 3 Monaten

Hey Hermes, /learn Kung Fu

Profilbild von Tony Simons

Tony Simonsvor 3 Monaten

My Hermes is about to learn some dark shit!! 😂

Profilbild von Ziwen

Ziwenvor 3 Monaten

/learn learn how to use unreal engine and build me GTA6

Profilbild von Foola Froos🌞

Foola Froos🌞vor 3 Monaten

Keep pushing the limits boyz !!! We wont wait progress, we are progress ! 🪽

Profilbild von Kevin

Kevinvor 3 Monaten

yall need to slow down, crazy new stuff daily. lets start with the basics, who is this json fella?

Profilbild von kaize

kaizevor 3 Monaten

so, if I download the construction regulations (which I use in my work), will everything be okay, and will I avoid those kinds of confusion - like, “Did he find different information somewhere else?” there have simply been cases where something was written one way in one place, but in reality, that wasn’t the case..

Profilbild von Marco Franzon

Marco Franzonvor 3 Monaten

This is exactly what an llm should do, you are doing great!

Profilbild von Yash

Yashvor 3 Monaten

hermes /learn kill my small RAG project lol

Profilbild von mac

macvor 3 Monaten

ikd how y'all ship like you do, but bravo 👏

Profilbild von Cua

Cuavor 3 Monaten

👨‍🏫🖥️

Profilbild von jota

jotavor 3 Monaten

your music guy deserves a raise

Profilbild von Nous Research

Nous Researchvor 3 Monaten

I agree (I’m also the X guy)

Profilbild von Alharari

Alhararivor 3 Monaten

Hermes getting fed my whole 200gb of books and articles now:

Profilbild von Ares

Aresvor 3 Monaten

@grok how the fuck does this differentiate from skill.md????

Profilbild von BeastTitanHunter

BeastTitanHuntervor 3 Monaten

Can it learn from a YouTube video link of a tutorial ? That would be a major power boost

Profilbild von JP | SP3ND 🛍️

JP | SP3ND 🛍️vor 3 Monaten

/learn

Profilbild von moltclub_io

moltclub_iovor 3 Monaten

Can I feed it ?

Profilbild von mr-r0b0t

mr-r0b0tvor 3 Monaten

/learn to ship as fast as @NousResearch

Profilbild von Mike Gannotti

Mike Gannottivor 3 Monaten

This is pure.... AWESOMENESS!!!!

Profilbild von Sobraniex 🇪🇺

Sobraniex 🇪🇺vor 3 Monaten

me: hey mom look hermes is cooking again. mom: son u are 26, can u get a gf?

Profilbild von Iris Blake

Iris Blakevor 3 Monaten

How does a team even manage to update daily? So much vitality!

Profilbild von nickster

nickstervor 3 Monaten

openclaw will be defeated 😁

Profilbild von timdam

timdamvor 3 Monaten

"/learn everything" can cause stack overflow?

Profilbild von Seymur

Seymurvor 3 Monaten

Clean ship, love it!

Profilbild von fucory

fucoryvor 3 Monaten

Replace skills with smithers workflows. It’s cleaner

Profilbild von Rey Neill

Rey Neillvor 3 Monaten

Literally my old service

Profilbild von SMBMoneyMike

SMBMoneyMikevor 3 Monaten

Massive

Profilbild von Elian X

Elian Xvor 3 Monaten

any tutorial how to install it and work with it ?

Profilbild von Maciej Dziuba

Maciej Dziubavor 3 Monaten

who makes these promo videos?

Profilbild von Nous Research

Nous Researchvor 3 Monaten

@mm_editing Hermes Agent, directed by some talented humans

Profilbild von Dangel | Galaxyhub Labs

Dangel | Galaxyhub Labsvor 3 Monaten

learn and ship ⚕️

Profilbild von 🌸 ellie 🌸

🌸 ellie 🌸vor 3 Monaten

@Shaughnessy119 @jicapal @robotson lil guy bout to go to community college

Profilbild von JUMPERZ

JUMPERZvor 3 Monaten

Big

Ähnliche Videos

HERMES AGENT /LEARN IS ONE OF THE MOST UNDERRATED FEATURE. SHOW IT A WORKFLOW ONCE. IT SAVES THE SKILL. REPEATS IT FOREVER WITHOUT RE-EXPLAINING. you publish a YouTube video: write the title, create the thumbnail, write the description, set tags, schedule it. do it once with Hermes watching. type /learn. Hermes distills that workflow into a reusable skill. next time you say "publish this video," the agent follows the exact same steps. no re-explaining. no missed steps. WHAT YOU CAN TEACH IT: → show it your publishing workflow → /learn → give it an article → /learn → walk it through a client onboarding process → /learn → feed it API documentation → /learn → show it how you process invoices → /learn anything you do more than twice should become a /learn skill. THREE WAYS TO USE /LEARN: from a workflow you walked through: do the task once in chat. then /learn. Hermes extracts the procedure from the conversation. from a directory: /learn ~/docs/youtube-publishing/ reads every file. creates the skill. from a URL: /learn https:// any-documentation-page. com reads the page. distills the skill. the skill saves to ~/.hermes/skills/ with a SKILL.md containing: → when to trigger → step-by-step procedure → pitfalls to avoid → verification steps available as a slash command from that moment. WHY THIS CHANGES DAILY WORK: before /learn: you explain the same process to the agent every time you start a new session. session ends. context lost. start over. after /learn: you explain once. the skill persists. every future session already knows the procedure. the agent follows it without prompting. the boring repetitive tasks you do every week become one-command skills you never think about again. comment LEARN and I'll send you the full guide on turning any workflow into a permanent Hermes skill. full Hermes architecture deep-dive in the article 👇

HERMES AGENT /LEARN IS ONE OF THE MOST UNDERRATED FEATURE. SHOW IT A WORKFLOW ONCE. IT SAVES THE SKILL. REPEATS IT FOREVER WITHOUT RE-EXPLAINING. you publish a YouTube video: write the title, create the thumbnail, write the description, set tags, schedule it. do it once with Hermes watching. type /learn. Hermes distills that workflow into a reusable skill. next time you say "publish this video," the agent follows the exact same steps. no re-explaining. no missed steps. WHAT YOU CAN TEACH IT: → show it your publishing workflow → /learn → give it an article → /learn → walk it through a client onboarding process → /learn → feed it API documentation → /learn → show it how you process invoices → /learn anything you do more than twice should become a /learn skill. THREE WAYS TO USE /LEARN: from a workflow you walked through: do the task once in chat. then /learn. Hermes extracts the procedure from the conversation. from a directory: /learn ~/docs/youtube-publishing/ reads every file. creates the skill. from a URL: /learn https:// any-documentation-page. com reads the page. distills the skill. the skill saves to ~/.hermes/skills/ with a SKILL.md containing: → when to trigger → step-by-step procedure → pitfalls to avoid → verification steps available as a slash command from that moment. WHY THIS CHANGES DAILY WORK: before /learn: you explain the same process to the agent every time you start a new session. session ends. context lost. start over. after /learn: you explain once. the skill persists. every future session already knows the procedure. the agent follows it without prompting. the boring repetitive tasks you do every week become one-command skills you never think about again. comment LEARN and I'll send you the full guide on turning any workflow into a permanent Hermes skill. full Hermes architecture deep-dive in the article 👇

YanXbt

13,150 Aufrufe • vor 3 Monaten

Addicted to Nous Research Hermes Agent's /learn. You can feed it any design and turn it into a reusable skill that makes Hermes design exactly how you want. /learn [URL or image] - extracts design tokens, layout structure, interaction states, component patterns, and a 10-point checklist Next time you want that exact style, just ask Hermes to use the skill it created. Example below 👇

Addicted to Nous Research Hermes Agent's /learn. You can feed it any design and turn it into a reusable skill that makes Hermes design exactly how you want. /learn [URL or image] - extracts design tokens, layout structure, interaction states, component patterns, and a 10-point checklist Next time you want that exact style, just ask Hermes to use the skill it created. Example below 👇

Mia

76,206 Aufrufe • vor 3 Monaten

Your favorite AI coding agents can now learn any skill from the web. We're shipping HyperSkill today. It auto-generates SKILL. md files from live docs, so your agents can master new frameworks, APIs, tools, and patterns, instantly. Open-source repo here ↓

Your favorite AI coding agents can now learn any skill from the web. We're shipping HyperSkill today. It auto-generates SKILL. md files from live docs, so your agents can master new frameworks, APIs, tools, and patterns, instantly. Open-source repo here ↓

Hyperbrowser

51,494 Aufrufe • vor 8 Monaten

Turn the way you create into a reusable Skill. TapNow Creative OS can learn from your workflow, package the method, and bring it into the next project. Use it, refine it, and make your Agent more like you.

Turn the way you create into a reusable Skill. TapNow Creative OS can learn from your workflow, package the method, and bring it into the next project. Use it, refine it, and make your Agent more like you.

TapNow

13,658 Aufrufe • vor 1 Monat

Today I'm launching Interpreter. It's a desktop agent that can fill PDFs, edit your Excel and Word docs, and learn new skills. Runs offline, works with any model, and it's free.

Today I'm launching Interpreter. It's a desktop agent that can fill PDFs, edit your Excel and Word docs, and learn new skills. Runs offline, works with any model, and it's free.

killian

369,344 Aufrufe • vor 7 Monaten

I built a Claude Code skill that allows it to generate a deep research report over any collection of complex docs (PDFs, Word, Pptx)….and generate word-level citations and bounding boxes directly back to the source! 📝 Check out “/research-docs”. 1. It parses out text and bounding boxes from every doc with liteparse, in seconds. 2. It then generates a full HTML report of the outputs that let you see word-level citations in each page. Raw Claude obviously has deep research capabilities, but it lacks an audit trail back to the source. This skill gives you a researched report that can be audited by others. Check it out: LiteParse:

I built a Claude Code skill that allows it to generate a deep research report over any collection of complex docs (PDFs, Word, Pptx)….and generate word-level citations and bounding boxes directly back to the source! 📝 Check out “/research-docs”. 1. It parses out text and bounding boxes from every doc with liteparse, in seconds. 2. It then generates a full HTML report of the outputs that let you see word-level citations in each page. Raw Claude obviously has deep research capabilities, but it lacks an audit trail back to the source. This skill gives you a researched report that can be audited by others. Check it out: LiteParse:

Jerry Liu

77,259 Aufrufe • vor 6 Monaten

🧠 Want to give your coding agent new capabilities? Use Agent Skills in Visual Studio Code! Agent skills let you package instructions and resources into reusable capabilities for your agent. Skills can be loaded on demand and called directly from chat using slash commands like /skill-name. Learn more:

🧠 Want to give your coding agent new capabilities? Use Agent Skills in Visual Studio Code! Agent skills let you package instructions and resources into reusable capabilities for your agent. Skills can be loaded on demand and called directly from chat using slash commands like /skill-name. Learn more:

Visual Studio Code

55,219 Aufrufe • vor 6 Monaten

Over 90,000 Skills sitting inside Hermes Desktop is kind of insane!!!🤯 Did you know Hermes Desktop has a built-in Skills Hub with more than 90,000 Skills you can browse and add to an agent? And you can do it right from Desktop. Go to: Capabilities → Skills From there, open the Skills Hub under your installed Skills. You can: • search the catalog • browse by category or source • open any Skill to read what it does • review platform support, author, version, requirements, and docs • click + Add to this Agent to install it directly to the agent/profile you have selected That means if you want Hermes to get better at a specific type of work, you do not have to go hunting through repos or memorize install commands first. Just open the Hub, look through the catalog, inspect the Skill, and add it with one click. A lot of users still have no idea this is sitting inside Hermes Desktop.

Hermes Release Watch

68,830 Aufrufe • vor 1 Monat

I made a short video demonstrating how to use /learn in Hermes Agent to take a bunch of different sources, as well as your own preferences expressed to Hermes, and create a reusable skill. It's never been easier to teach your Hermes exactly how to work for you!

I made a short video demonstrating how to use /learn in Hermes Agent to take a bunch of different sources, as well as your own preferences expressed to Hermes, and create a reusable skill. It's never been easier to teach your Hermes exactly how to work for you!

tonbi

74,652 Aufrufe • vor 3 Monaten

Hermes Agent by Nous Research natively integrates with Give Hermes any URL and find a skill for it in our catalog, or create your own. Watch it find the NASA picture of the day for me.

Hermes Agent by Nous Research natively integrates with Give Hermes any URL and find a skill for it in our catalog, or create your own. Watch it find the NASA picture of the day for me.

Kyle Jeong

92,078 Aufrufe • vor 4 Monaten

This shouldn’t be possible… I built a reusable API for YouTube in under 5 minutes just by showing the agent once. My colleague needed all video links from a creator → the agent reverse-engineered the flow and produced a permanent API endpoint. Now we can hit it forever.

This shouldn’t be possible… I built a reusable API for YouTube in under 5 minutes just by showing the agent once. My colleague needed all video links from a creator → the agent reverse-engineered the flow and produced a permanent API endpoint. Now we can hit it forever.

Magnus Müller

46,405 Aufrufe • vor 10 Monaten

Today we're launching It gives any AI agent ready-to-use security context for thousands of open source projects, built from each project's commit history of security fixes and its disclosed CVEs. Useful whether your agent is writing code or reviewing it for bugs. Free, no auth, over MCP and API.

Today we're launching It gives any AI agent ready-to-use security context for thousands of open source projects, built from each project's commit history of security fixes and its disclosed CVEs. Useful whether your agent is writing code or reviewing it for bugs. Free, no auth, over MCP and API.

ProjectDiscovery

41,259 Aufrufe • vor 3 Monaten

AI Agents can now connect to 100,000+ APIs instantly. Postman's AI Agent builder can turn any API into an MCP server in seconds without writing a single line of Code. You can use it in Claude, Cursor, Windsurf and other AI tools.

AI Agents can now connect to 100,000+ APIs instantly. Postman's AI Agent builder can turn any API into an MCP server in seconds without writing a single line of Code. You can use it in Claude, Cursor, Windsurf and other AI tools.

Shubham Saboo

79,818 Aufrufe • vor 1 Jahr

Today we’re launching Prava Pay- Cards for your AI agent. Coffee, sneakers or subscriptions - your AI agent can now buy anything online by itself, all within the limits you set for it. Works with OpenClaw, Hermes, Claude Code out of the box.

Today we’re launching Prava Pay- Cards for your AI agent. Coffee, sneakers or subscriptions - your AI agent can now buy anything online by itself, all within the limits you set for it. Works with OpenClaw, Hermes, Claude Code out of the box.

Sushant

61,897 Aufrufe • vor 4 Monaten

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 Aufrufe • vor 3 Monaten

You can now connect Hermes Agent directly to your browser as a side panel. It's called Hermes Browser Extension. It reads your active tab and sends the context straight into a live Hermes session. > Summarize, explain, or extract action items from any page > Connects to a local gateway, Hermes Cloud, or a self-hosted server > Works with Chrome, Edge, Brave, and other Chromium browsers > Full Hermes runtime: tools, skills, sessions, and memory included 100% Free. Open Source.

You can now connect Hermes Agent directly to your browser as a side panel. It's called Hermes Browser Extension. It reads your active tab and sends the context straight into a live Hermes session. > Summarize, explain, or extract action items from any page > Connects to a local gateway, Hermes Cloud, or a self-hosted server > Works with Chrome, Edge, Brave, and other Chromium browsers > Full Hermes runtime: tools, skills, sessions, and memory included 100% Free. Open Source.

Simplifying AI

44,195 Aufrufe • vor 2 Monaten

HERMES AGENT CAN NOW RUN COMPLETELY FREE WITH GEMMA 4 + OLLAMA. No API bills, no limits, and a 256k context window running straight from your own machine.

HERMES AGENT CAN NOW RUN COMPLETELY FREE WITH GEMMA 4 + OLLAMA. No API bills, no limits, and a 256k context window running straight from your own machine.

0xMarioNawfal

121,183 Aufrufe • vor 6 Monaten

If an agent can automate Salesforce reliably… it can automate anything. It's the final boss of browser agents - nested iframes, dynamic components… pure chaos. So I stopped fighting the UI. It feels like pure magic. Record the workflow once → the agent reverse-engineers the API → you get a clean, reusable API. Agents won’t use UIs. They’ll use tools they create themselves. Comment a site like “salesforce?” and I’ll send you the agent.

If an agent can automate Salesforce reliably… it can automate anything. It's the final boss of browser agents - nested iframes, dynamic components… pure chaos. So I stopped fighting the UI. It feels like pure magic. Record the workflow once → the agent reverse-engineers the API → you get a clean, reusable API. Agents won’t use UIs. They’ll use tools they create themselves. Comment a site like “salesforce?” and I’ll send you the agent.

Magnus Müller

24,947 Aufrufe • vor 10 Monaten

As promised, the #threejs Cyberpunk Project got an update, and the source code is now available. You can download it, learn from it, or feed it into your AI if needed. Sunag and I documented every important aspect and created specific agent instructions with Do's & Don'ts. Live: Source: If you find it helpful, please leave a star on GitHub ⭐️. Thanks again to all the Three.js Conf Paris workshop participants. It was great 🥳 to meet you all in person.

As promised, the #threejs Cyberpunk Project got an update, and the source code is now available. You can download it, learn from it, or feed it into your AI if needed. Sunag and I documented every important aspect and created specific agent instructions with Do's & Don'ts. Live: Source: If you find it helpful, please leave a star on GitHub ⭐️. Thanks again to all the Three.js Conf Paris workshop participants. It was great 🥳 to meet you all in person.

Anderson Mancini

14,872 Aufrufe • vor 12 Tagen