Загрузка видео...

Не удалось загрузить видео

На главную

I've combined Manim Nous Research's Hermes Agent skill + 's Math Code. Math Code executes the proof on a problem called Jordan's Lemma and Hermes Agent with Claude Sonnet 3.7 directs Math Code, writes a script, gets Manim to render an explanatory video. Jordan's Lemma: It helps to simplify...

prompterminal's profile picture

Jeanne

1,843 subscribers

142,115 просмотров • 4 месяцев назад •via X (Twitter)

ИскусствоОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

HERMES AGENT CAN CREATE VIDEOS. NOT WITH AN API CALL. IT WRITES THE CODE, RENDERS THE SCENES, AND STITCHES THEM INTO AN MP4. the video attached to this post was generated by Hermes Agent using manim-video skill. three bundled video skills most people skip: 1. MANIM VIDEO 3Blue1Brown-style animated explainers. algorithm visualizations, equation derivations, architecture diagrams, data stories. the pipeline: PLAN → CODE → RENDER → STITCH → AUDIO → REVIEW Hermes writes a plan.md with narrative arc and scene list. then codes a Python script with one class per scene. renders each scene through Manim CE. stitches clips with ffmpeg. adds voiceover if you want it. requirements: → Python 3.10+ → Manim Community Edition v0.20+ → LaTeX (texlive-full) → ffmpeg → no GPU needed draft quality: manim -ql production quality: manim -qh 2. HYPERFRAMES complement to manim-video. use manim for math and algorithms. use hyperframes for everything else: motion graphics, talking-head with captions, product tours, social overlays, shader transitions. HTML is the source of truth. GSAP timeline for animation. CSS for appearance. HyperFrames engine captures frame-by-frame and encodes to MP4 or WebM with ffmpeg. 3. KANBAN VIDEO ORCHESTRATOR this is the advanced play. a multi-agent video production pipeline backed by Hermes Kanban. it creates profiles for each video role. a director profile decomposes the project into kanban tasks. renderer profiles pick up scenes and produce them. the orchestrator decides which skill fits each scene: manim-video for math, hyperframes for motion graphics, p5js for generative art, blender-mcp for 3D, ascii-video for terminal aesthetics. one prompt. multiple agents. one final video. HOW TO USE: enable any of these: /skills search manim /skills search hyperframes /skills search video or ask directly: "create a 60-second explainer video about how the self-improvement loop works in Hermes Agent. use manim style. dark background, amber and teal accents." Hermes writes the plan, codes every scene, renders, stitches, and delivers an MP4. you review and publish. comment MANIM and I'll send you the exact prompt I used to generate the video in this post. full Hermes NIGHT MODE WORKFLOW 👇
1:41

HERMES AGENT CAN CREATE VIDEOS. NOT WITH AN API CALL. IT WRITES THE CODE, RENDERS THE SCENES, AND STITCHES THEM INTO AN MP4. the video attached to this post was generated by Hermes Agent using manim-video skill. three bundled video skills most people skip: 1. MANIM VIDEO 3Blue1Brown-style animated explainers. algorithm visualizations, equation derivations, architecture diagrams, data stories. the pipeline: PLAN → CODE → RENDER → STITCH → AUDIO → REVIEW Hermes writes a plan.md with narrative arc and scene list. then codes a Python script with one class per scene. renders each scene through Manim CE. stitches clips with ffmpeg. adds voiceover if you want it. requirements: → Python 3.10+ → Manim Community Edition v0.20+ → LaTeX (texlive-full) → ffmpeg → no GPU needed draft quality: manim -ql production quality: manim -qh 2. HYPERFRAMES complement to manim-video. use manim for math and algorithms. use hyperframes for everything else: motion graphics, talking-head with captions, product tours, social overlays, shader transitions. HTML is the source of truth. GSAP timeline for animation. CSS for appearance. HyperFrames engine captures frame-by-frame and encodes to MP4 or WebM with ffmpeg. 3. KANBAN VIDEO ORCHESTRATOR this is the advanced play. a multi-agent video production pipeline backed by Hermes Kanban. it creates profiles for each video role. a director profile decomposes the project into kanban tasks. renderer profiles pick up scenes and produce them. the orchestrator decides which skill fits each scene: manim-video for math, hyperframes for motion graphics, p5js for generative art, blender-mcp for 3D, ascii-video for terminal aesthetics. one prompt. multiple agents. one final video. HOW TO USE: enable any of these: /skills search manim /skills search hyperframes /skills search video or ask directly: "create a 60-second explainer video about how the self-improvement loop works in Hermes Agent. use manim style. dark background, amber and teal accents." Hermes writes the plan, codes every scene, renders, stitches, and delivers an MP4. you review and publish. comment MANIM and I'll send you the exact prompt I used to generate the video in this post. full Hermes NIGHT MODE WORKFLOW 👇

YanXbt

32,494 просмотров • 1 месяц назад

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👇
20:54

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

22,667 просмотров • 29 дней назад

Axiom Math founder Carina Hong on why math is the path to general superintelligence: “Math is the sandbox for reality. You very quickly see verifiable rewards because in math, there’s an absolute right or wrong.” “And especially when you have Lean, you can check the proof or solution step by step. You’ll be able to apply reinforcement learning in a much more efficient way.” “We have currently scaled from winning a Putnam perfect score to solving a batch of research problems that professional mathematicians find really challenging. And we also see this transfer to code verification.”
0:56

Axiom Math founder Carina Hong on why math is the path to general superintelligence: “Math is the sandbox for reality. You very quickly see verifiable rewards because in math, there’s an absolute right or wrong.” “And especially when you have Lean, you can check the proof or solution step by step. You’ll be able to apply reinforcement learning in a much more efficient way.” “We have currently scaled from winning a Putnam perfect score to solving a batch of research problems that professional mathematicians find really challenging. And we also see this transfer to code verification.”

TBPN

39,589 просмотров • 4 месяцев назад

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!
12:40

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!

Sebastian Schöner

13,033 просмотров • 3 месяцев назад

HERMES AGENT NOW RUNS A FULL BUSINESS FOR $8/MONTH. CONTENT. CODE. INBOX. ALL AGENTS. EVERYTHING WHILE YOU SLEEP. one user built this in one session. zero terminal commands. browser only. the team: → content agent: finds video topics, writes first drafts, helps with animations → code builder: writes website and SaaS code → ops agent: organizes and answers email total setup cost: $1. monthly runtime: $8 VPS + cheap model API. the trick is matching model to task. frontier models (Opus 4.8, GPT-5.5) for complex /goals only. $5/million tokens. mid-tier (Claude Sonnet, Haiku, Kimiko 2.6) for daily content and research work. budget (DeepSeek V4 Flash, MiniMax 2.7, Gemma 4, Qwen 3) for cron jobs and routine. run the initial setup on Opus. switch to DeepSeek for everything after. your bill drops 90% with zero quality loss on routine work. the agent team picks up tasks from kanban. each completed task creates a skill. week 3 the same workflows run faster than week 1. full breakdown on Hermes Os in the article 👇
14:53

HERMES AGENT NOW RUNS A FULL BUSINESS FOR $8/MONTH. CONTENT. CODE. INBOX. ALL AGENTS. EVERYTHING WHILE YOU SLEEP. one user built this in one session. zero terminal commands. browser only. the team: → content agent: finds video topics, writes first drafts, helps with animations → code builder: writes website and SaaS code → ops agent: organizes and answers email total setup cost: $1. monthly runtime: $8 VPS + cheap model API. the trick is matching model to task. frontier models (Opus 4.8, GPT-5.5) for complex /goals only. $5/million tokens. mid-tier (Claude Sonnet, Haiku, Kimiko 2.6) for daily content and research work. budget (DeepSeek V4 Flash, MiniMax 2.7, Gemma 4, Qwen 3) for cron jobs and routine. run the initial setup on Opus. switch to DeepSeek for everything after. your bill drops 90% with zero quality loss on routine work. the agent team picks up tasks from kanban. each completed task creates a skill. week 3 the same workflows run faster than week 1. full breakdown on Hermes Os in the article 👇

YanXbt

30,910 просмотров • 1 месяц назад

I turned cursor + claude 3.7 into a powerhouse content writer using a custom agent mode. it: - researches your topic - plans out your content - writes one section at a time - has full context of previously written sections - adds relevant links, tables, code examples, etc - writes for users NOT seo slop watch the video - it literally one-shot a killer article in minutes and the output looks nothing like AI check the link to the article in the first reply below if this post gets a million views i'll share the custom agent instructions prompt ;)
0:45

I turned cursor + claude 3.7 into a powerhouse content writer using a custom agent mode. it: - researches your topic - plans out your content - writes one section at a time - has full context of previously written sections - adds relevant links, tables, code examples, etc - writes for users NOT seo slop watch the video - it literally one-shot a killer article in minutes and the output looks nothing like AI check the link to the article in the first reply below if this post gets a million views i'll share the custom agent instructions prompt ;)

Ian Nuttall

117,186 просмотров • 1 год назад

IN 1986 MIT FILMED THE LECTURE WHERE CODE STOPPED BEING CODE AND BECAME DATA 43 minutes from Gerald Sussman, in the most legendary intro programming course ever recorded. -> The idea that lands: to a program, your code is just data it can read and rewrite. He builds a program that does real calculus -- not by crunching numbers, but by reading the math as a list and transforming it piece by piece. Then he shows the trick hiding under all of it: in this language, code and data are the same material. Forty years later that is exactly what an AI coding agent is -- a program that reads your code as data, rewrites it, and hands it back. Sussman drew the whole idea on a blackboard in 1986. Writing code was never the deepest skill -- understanding that code itself is data a program can manipulate is. This is where you learn it. Most people think AI writing code is brand new. The ones who watch this saw the blueprint 40 years ago. Bookmark & Watch it. This one's a legend ↓
43:30

IN 1986 MIT FILMED THE LECTURE WHERE CODE STOPPED BEING CODE AND BECAME DATA 43 minutes from Gerald Sussman, in the most legendary intro programming course ever recorded. -> The idea that lands: to a program, your code is just data it can read and rewrite. He builds a program that does real calculus -- not by crunching numbers, but by reading the math as a list and transforming it piece by piece. Then he shows the trick hiding under all of it: in this language, code and data are the same material. Forty years later that is exactly what an AI coding agent is -- a program that reads your code as data, rewrites it, and hands it back. Sussman drew the whole idea on a blackboard in 1986. Writing code was never the deepest skill -- understanding that code itself is data a program can manipulate is. This is where you learn it. Most people think AI writing code is brand new. The ones who watch this saw the blueprint 40 years ago. Bookmark & Watch it. This one's a legend ↓

slash1s

22,107 просмотров • 1 месяц назад

How to build an AI SEO Loop with Claude Code. I just launched a Free course on how to setup Claude Code, Hermes, Codex or any agent to become your Chief SEO that gets you customers on autopilot. Comment "Loop" and I'll send an access in your DMs. You'll learn: - How to install the SEO Skill. - Audit and Fix your website through Google Search Console. - Find keywords that convert. - Publish content automatically. - Track your positions on Google and your AI visibility. - Get recommended by AI. - and more bonuses.
7:36

How to build an AI SEO Loop with Claude Code. I just launched a Free course on how to setup Claude Code, Hermes, Codex or any agent to become your Chief SEO that gets you customers on autopilot. Comment "Loop" and I'll send an access in your DMs. You'll learn: - How to install the SEO Skill. - Audit and Fix your website through Google Search Console. - Find keywords that convert. - Publish content automatically. - Track your positions on Google and your AI visibility. - Get recommended by AI. - and more bonuses.

Florian Darroman

23,852 просмотров • 1 месяц назад

You can easily rewrite most automations I've seen using Claude Code and Codex by replacing them with a script. Why would you spend tokens running deterministic workflows? In this video, I'll show you: • An automation using Zapier's SDK • When to use the SDK and when the MCP
7:51

You can easily rewrite most automations I've seen using Claude Code and Codex by replacing them with a script. Why would you spend tokens running deterministic workflows? In this video, I'll show you: • An automation using Zapier's SDK • When to use the SDK and when the MCP

Santiago

29,103 просмотров • 2 месяцев назад

HERMES AGENT WITHOUT TOOLS IS A CHATBOT. WITH THEM IT BUILDS 3D TOWERS IN BLENDER, CHECKS STOCK PRICES, AND DRIVES VS CODE. tonbi JUST DROPPED THE FULL GUIDE. module 6 of his 10-part Hermes masterclass. best breakdown of the tool layer anyone has published. what you need to know: TOOLS vs SKILLS vs MCP skills = instructions (markdown, loaded into context) tools = callable functions (Python, agent emits call, Hermes executes) MCP = adapters to external systems (Blender, Stripe, Linear, Notion) every tool has three parts: → the function (does the real work) → the schema (what the model sees to decide when to call it) → the registry (makes the tool exist in the agent) the model never runs the function directly. it emits a structured request (tool name + JSON args). Hermes executes and returns the result. if the tool fails, the error goes back as JSON. the agent recovers instead of crashing. TOOL SETS CONTROL THE SURFACE hermes chat --tool-sets web # only web tools loaded. no files, no terminal. hermes chat --tool-sets safe # read-only: web search, vision, image gen. # no file writes. no terminal. no code execution. mid-session: /tools enable video /tools disable terminal or toggle in the dashboard: hermes dashboard → Skills → Tool Sets MCP SERVERS two transport types: STDIO (local subprocess) or HTTP (remote endpoint). add a server: hermes mcp # or ask: "add the MCP server for Blender" filter tools with include/exclude per server. keep only what you trust. security: → OAuth 2.1 PKCE (no long-lived tokens in config) → package scanning via api.osv. dev before launch → all MCP calls go through approval gates HERMES AS MCP SERVER hermes mcp serve exposes 10 tools via FastMCP. connect VS Code Copilot or Cursor to your running Hermes instance. BUILD YOUR OWN TOOL He built a stock price tool live: → Python function calling Finnhub API → schema with name, description, parameters → registered in tool_sets.py → agent calls it automatically when relevant any repeating API call in your workflow can become a native tool. full Hermes architecture deep-dive in the article 👇
26:15

HERMES AGENT WITHOUT TOOLS IS A CHATBOT. WITH THEM IT BUILDS 3D TOWERS IN BLENDER, CHECKS STOCK PRICES, AND DRIVES VS CODE. tonbi JUST DROPPED THE FULL GUIDE. module 6 of his 10-part Hermes masterclass. best breakdown of the tool layer anyone has published. what you need to know: TOOLS vs SKILLS vs MCP skills = instructions (markdown, loaded into context) tools = callable functions (Python, agent emits call, Hermes executes) MCP = adapters to external systems (Blender, Stripe, Linear, Notion) every tool has three parts: → the function (does the real work) → the schema (what the model sees to decide when to call it) → the registry (makes the tool exist in the agent) the model never runs the function directly. it emits a structured request (tool name + JSON args). Hermes executes and returns the result. if the tool fails, the error goes back as JSON. the agent recovers instead of crashing. TOOL SETS CONTROL THE SURFACE hermes chat --tool-sets web # only web tools loaded. no files, no terminal. hermes chat --tool-sets safe # read-only: web search, vision, image gen. # no file writes. no terminal. no code execution. mid-session: /tools enable video /tools disable terminal or toggle in the dashboard: hermes dashboard → Skills → Tool Sets MCP SERVERS two transport types: STDIO (local subprocess) or HTTP (remote endpoint). add a server: hermes mcp # or ask: "add the MCP server for Blender" filter tools with include/exclude per server. keep only what you trust. security: → OAuth 2.1 PKCE (no long-lived tokens in config) → package scanning via api.osv. dev before launch → all MCP calls go through approval gates HERMES AS MCP SERVER hermes mcp serve exposes 10 tools via FastMCP. connect VS Code Copilot or Cursor to your running Hermes instance. BUILD YOUR OWN TOOL He built a stock price tool live: → Python function calling Finnhub API → schema with name, description, parameters → registered in tool_sets.py → agent calls it automatically when relevant any repeating API call in your workflow can become a native tool. full Hermes architecture deep-dive in the article 👇

YanXbt

32,680 просмотров • 1 месяц назад

Claude Code over Excel++ 🤖📊 Claude already 'works' over Excel, but in a naive manner - it writes raw python/openpyxl to analyze an Excel sheet cell-by-cell and generally lacks a semantic understanding of the content. Basically the coding abstractions used are too low-level to have the coding agent accurately do more sophisticated analysis. Our new LlamaSheets API lets you automatically segment structure complex Excel sheets into well-formatted 2D tables. This both gives Claude Code immediate semantic awareness of the sheet, and allows it to run Pandas/SQL over well-structured dataframes. We've written a guide showing you how specifically to use LlamaSheets with coding agents! Guide: Sign up to LlamaCloud:
0:46

Claude Code over Excel++ 🤖📊 Claude already 'works' over Excel, but in a naive manner - it writes raw python/openpyxl to analyze an Excel sheet cell-by-cell and generally lacks a semantic understanding of the content. Basically the coding abstractions used are too low-level to have the coding agent accurately do more sophisticated analysis. Our new LlamaSheets API lets you automatically segment structure complex Excel sheets into well-formatted 2D tables. This both gives Claude Code immediate semantic awareness of the sheet, and allows it to run Pandas/SQL over well-structured dataframes. We've written a guide showing you how specifically to use LlamaSheets with coding agents! Guide: Sign up to LlamaCloud:

Jerry Liu

75,897 просмотров • 8 месяцев назад

What's the actual setup work behind running a team of AI agents on Buzz? Almost none. The one move that mattered: pin each agent to a model. "Fizz is a Fable model and Honey is Sonnet" Certain tasks don't need Fable's power, and running them there burns through tokens fast. Then I made a chief agent officer — an agent whose only job is deciding which agent gets the task. Copywriter, brainstormer, code reviewer. You forget who they all are. It doesn't. Claude Code is the harness underneath, and every skill you've already got installed globally comes with it. The catch: this is early preview software, maybe alpha. Recurring tasks and workflows "weren't really landing great," and the relay round-trip to the server makes it slower than sitting in Claude Code directly. Solopreneurs and small teams iterating on small ideas, this is a great tool. Complex software engineering, not yet. Just start playing around.
3:24

What's the actual setup work behind running a team of AI agents on Buzz? Almost none. The one move that mattered: pin each agent to a model. "Fizz is a Fable model and Honey is Sonnet" Certain tasks don't need Fable's power, and running them there burns through tokens fast. Then I made a chief agent officer — an agent whose only job is deciding which agent gets the task. Copywriter, brainstormer, code reviewer. You forget who they all are. It doesn't. Claude Code is the harness underneath, and every skill you've already got installed globally comes with it. The catch: this is early preview software, maybe alpha. Recurring tasks and workflows "weren't really landing great," and the relay round-trip to the server makes it slower than sitting in Claude Code directly. Solopreneurs and small teams iterating on small ideas, this is a great tool. Complex software engineering, not yet. Just start playing around.

The Startup Ideas Podcast (SIP) 🧃

24,144 просмотров • 4 дней назад

HERMES AGENT + OBSIDIAN IS A COMBINATION NOBODY IS TALKING ABOUT. Hermes ships with a bundled Obsidian skill. read, search, and create notes in your vault out of the box. why this combination is powerful: Hermes built-in memory is capped. MEMORY.md: 2,200 chars (~800 tokens). USER.md: 1,375 chars (~500 tokens). Obsidian vault has no cap. your agent writes research, session summaries, project context, and learned patterns as linked markdown notes. unlimited depth. the agent creates indexed notes by design. timestamps, backlinks, tags. every note connects to the knowledge graph. three ways to integrate: 1. BUNDLED OBSIDIAN SKILL (simplest) ships with Hermes. reads, searches, creates notes in your vault directly. hermes skills list | grep obsidian 2. OBSIDIAN MCP SERVER (deepest) 30+ tools: full-text search, tag lookup, note management, vault analysis, link analysis, orphan detection. add it via: hermes mcp 3. TELEGRAM + CRON → VAULT (always-on) set a cron job that writes daily summaries, research findings, or task reports directly into your Obsidian vault. your agent feeds the vault while you sleep. you review in Obsidian when you're ready. the unlock: Hermes memory handles what the agent needs to know per session (capped, injected). Obsidian handles everything the agent has ever learned (uncapped, searchable). short-term in Hermes. long-term in Obsidian. both accessible. both persistent. keep the vault scope narrow at first. start with one /Hermes folder. expand once you trust the workflow. 8 Loops Indise Hermes Agent👇
0:56

HERMES AGENT + OBSIDIAN IS A COMBINATION NOBODY IS TALKING ABOUT. Hermes ships with a bundled Obsidian skill. read, search, and create notes in your vault out of the box. why this combination is powerful: Hermes built-in memory is capped. MEMORY.md: 2,200 chars (~800 tokens). USER.md: 1,375 chars (~500 tokens). Obsidian vault has no cap. your agent writes research, session summaries, project context, and learned patterns as linked markdown notes. unlimited depth. the agent creates indexed notes by design. timestamps, backlinks, tags. every note connects to the knowledge graph. three ways to integrate: 1. BUNDLED OBSIDIAN SKILL (simplest) ships with Hermes. reads, searches, creates notes in your vault directly. hermes skills list | grep obsidian 2. OBSIDIAN MCP SERVER (deepest) 30+ tools: full-text search, tag lookup, note management, vault analysis, link analysis, orphan detection. add it via: hermes mcp 3. TELEGRAM + CRON → VAULT (always-on) set a cron job that writes daily summaries, research findings, or task reports directly into your Obsidian vault. your agent feeds the vault while you sleep. you review in Obsidian when you're ready. the unlock: Hermes memory handles what the agent needs to know per session (capped, injected). Obsidian handles everything the agent has ever learned (uncapped, searchable). short-term in Hermes. long-term in Obsidian. both accessible. both persistent. keep the vault scope narrow at first. start with one /Hermes folder. expand once you trust the workflow. 8 Loops Indise Hermes Agent👇

YanXbt

20,617 просмотров • 1 месяц назад

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.
3:25

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Santiago

64,425 просмотров • 8 месяцев назад

here's a hands on guide to setup multi-agent autoresearch by Andrej Karpathy. uses open models. works with codex, claude, open code. - uses 5 agents each with a configuration, specific tools, roles, and permission (see repo) - a researcher agent searches papers on hf papers and creates hypotheses - a planner agent maintains an experiment plan and log - workers take the hypotheses and updates the scripts, then it starts a hf job with a gpu to run the script - a reporter agent monitors these jobs and reports events and metrics to a TrackioApp dashboard I ran this for 4 hours and the agents ran 32 jobs, they improved on the baseline by a small margin. check out everything I learnt in thread.
9:09

here's a hands on guide to setup multi-agent autoresearch by Andrej Karpathy. uses open models. works with codex, claude, open code. - uses 5 agents each with a configuration, specific tools, roles, and permission (see repo) - a researcher agent searches papers on hf papers and creates hypotheses - a planner agent maintains an experiment plan and log - workers take the hypotheses and updates the scripts, then it starts a hf job with a gpu to run the script - a reporter agent monitors these jobs and reports events and metrics to a TrackioApp dashboard I ran this for 4 hours and the agents ran 32 jobs, they improved on the baseline by a small margin. check out everything I learnt in thread.

Ben Burtenshaw

90,641 просмотров • 3 месяцев назад

Anthropic just released a talk on building headless automation with Claude Code. Presented by Sid Bidasaria, Member of Technical Staff at Anthropic live at Code with Claude on May 22, 2025 in San Francisco. Here is what the talk covers. Headless mode lets you run Claude Code without a person actively typing prompts from inside an automated script. Instead of a live session, a script calls Claude with a pre-written instruction using the -p flag. This opens the door for Claude Code to become a piece of a much larger, automated process. In plain terms: Claude Code stops being a tool you use and starts being a service that runs on its own. What this unlocks: Scheduled tasks: Run Claude Code on a cron schedule without anyone at a keyboard. Fix linting errors across an entire codebase. Automatically. Overnight. CI/CD integration: Trigger Claude Code as a step in your build process. Open a PR. Claude reviews it, flags issues, and pushes fixes before a human ever looks at it. GitHub automation: A project manager comments "Claude fix this" on a GitHub issue. Claude reads the request, finds the code, writes the fix, and opens the PR. Multi-machine workflows: One orchestrator dispatches tasks to multiple Claude Code instances running in parallel across different repos simultaneously. When you combine headless mode, hooks, and GitHub Actions, development teams can automate tasks that usually eat up significant time freeing senior engineers to focus on architectural problems while Claude handles the repetitive ones. If you use Claude Code for anything beyond single sessions this talk is worth 20 minutes of your time.
20:58

Anthropic just released a talk on building headless automation with Claude Code. Presented by Sid Bidasaria, Member of Technical Staff at Anthropic live at Code with Claude on May 22, 2025 in San Francisco. Here is what the talk covers. Headless mode lets you run Claude Code without a person actively typing prompts from inside an automated script. Instead of a live session, a script calls Claude with a pre-written instruction using the -p flag. This opens the door for Claude Code to become a piece of a much larger, automated process. In plain terms: Claude Code stops being a tool you use and starts being a service that runs on its own. What this unlocks: Scheduled tasks: Run Claude Code on a cron schedule without anyone at a keyboard. Fix linting errors across an entire codebase. Automatically. Overnight. CI/CD integration: Trigger Claude Code as a step in your build process. Open a PR. Claude reviews it, flags issues, and pushes fixes before a human ever looks at it. GitHub automation: A project manager comments "Claude fix this" on a GitHub issue. Claude reads the request, finds the code, writes the fix, and opens the PR. Multi-machine workflows: One orchestrator dispatches tasks to multiple Claude Code instances running in parallel across different repos simultaneously. When you combine headless mode, hooks, and GitHub Actions, development teams can automate tasks that usually eat up significant time freeing senior engineers to focus on architectural problems while Claude handles the repetitive ones. If you use Claude Code for anything beyond single sessions this talk is worth 20 minutes of your time.

Elias

14,096 просмотров • 2 месяцев назад

HERMES + ELEVENLABS TURNED A $3,000/MO ANSWERING SERVICE INTO A ~$145/MO AI THAT NEVER MISSES A CALL. A missed call after 6pm isn't a missed call. It's a customer booking with your competitor. Most businesses pay $2,000-$4,000/mo for a human to make sure that doesn't happen. Last week I gave my Hermes Agent a real phone number instead. It answers every call, 24/7, in a natural ElevenLabs voice. It doesn't read a script - it checks the calendar, recognizes the caller, and books the appointment mid-call. The math on one dental clinic: → Old answering service: ~$2,400/mo (messages only) → Hermes + ElevenLabs: ~$145/mo (books in real time) → ~$27,000/yr saved per location And it's strictly better - it books at 11pm instead of leaving a voicemail. The setup is one afternoon: → Turn on Hermes' API server → Tunnel it with ngrok → Point an ElevenLabs agent at it (Custom LLM) → Attach a Twilio number Reply "ElevenLabs" + RT, and I’ll send you the detailed playbook via DM Full step-by-step build 👇
2:18

HERMES + ELEVENLABS TURNED A $3,000/MO ANSWERING SERVICE INTO A ~$145/MO AI THAT NEVER MISSES A CALL. A missed call after 6pm isn't a missed call. It's a customer booking with your competitor. Most businesses pay $2,000-$4,000/mo for a human to make sure that doesn't happen. Last week I gave my Hermes Agent a real phone number instead. It answers every call, 24/7, in a natural ElevenLabs voice. It doesn't read a script - it checks the calendar, recognizes the caller, and books the appointment mid-call. The math on one dental clinic: → Old answering service: ~$2,400/mo (messages only) → Hermes + ElevenLabs: ~$145/mo (books in real time) → ~$27,000/yr saved per location And it's strictly better - it books at 11pm instead of leaving a voicemail. The setup is one afternoon: → Turn on Hermes' API server → Tunnel it with ngrok → Point an ElevenLabs agent at it (Custom LLM) → Attach a Twilio number Reply "ElevenLabs" + RT, and I’ll send you the detailed playbook via DM Full step-by-step build 👇

ZEUS⚡️

10,383 просмотров • 2 месяцев назад

Claude Code creator: "100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too. The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops" in this interview he breaks down exactly how a system changes everything: - the memory and context features that turn Claude into a second brain - the knowledge architecture most users don't know Claude can build - the integration layer that connects Claude to your actual workflow - why typing one question at a time is the most expensive way to use Claude if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed full guide in the article below
50:12

Claude Code creator: "100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too. The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops" in this interview he breaks down exactly how a system changes everything: - the memory and context features that turn Claude into a second brain - the knowledge architecture most users don't know Claude can build - the integration layer that connects Claude to your actual workflow - why typing one question at a time is the most expensive way to use Claude if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed full guide in the article below

Khairallah AL-Awady

39,243 просмотров • 1 месяц назад

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.
0:34

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

SIBYL

81,361 просмотров • 2 месяцев назад

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!
2:17

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 просмотров • 1 год назад