Loading video...

Video Failed to Load

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

Helmor has been out as an open-source coding agent orchestrator for less than a week, and we’re already close to 1,000 GitHub stars!!! As a little gift, we shipped a new feature you’re going to love. 👇 Stop copy-pasting GitHub links, Linear tickets, Slack threads, and random notes into... show more

Caspian 東澔

1,423 subscribers

10,814 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

GITHUB JUST KILLED THE WORST PART OF VIBE CODING they shipped a free tool called Spec Kit and it already crossed 120,000 stars the fix is stupidly simple instead of tossing vague prompts at an agent and praying it doesn't wreck your project Spec Kit makes the AI write a full structured spec before it touches a single line of code it works through the problem first figures out what you want to build asks about the gaps lays out the project then it starts coding you get fewer insane bugs, cleaner output and results you can predict the flow looks like this: /constitution for your rules and standards /specify for what you want to build /clarify for the open questions before you start /plan for architecture and stack /tasks for the ordered work /implement to run it it plugs into Claude Code, Cursor, Copilot, Codex, Gemini CLI and 25+ other agents 120,000 stars, 10,000 forks, open source, shipped by GitHub itself learning to drive agents like this is most of what separates people getting hired as AI engineers from everyone still fighting their prompts

GITHUB JUST KILLED THE WORST PART OF VIBE CODING they shipped a free tool called Spec Kit and it already crossed 120,000 stars the fix is stupidly simple instead of tossing vague prompts at an agent and praying it doesn't wreck your project Spec Kit makes the AI write a full structured spec before it touches a single line of code it works through the problem first figures out what you want to build asks about the gaps lays out the project then it starts coding you get fewer insane bugs, cleaner output and results you can predict the flow looks like this: /constitution for your rules and standards /specify for what you want to build /clarify for the open questions before you start /plan for architecture and stack /tasks for the ordered work /implement to run it it plugs into Claude Code, Cursor, Copilot, Codex, Gemini CLI and 25+ other agents 120,000 stars, 10,000 forks, open source, shipped by GitHub itself learning to drive agents like this is most of what separates people getting hired as AI engineers from everyone still fighting their prompts

Atlas

501,832 views • 1 month ago

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 views • 12 days ago

Alright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.

Alright, now that we know what an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.

Google AI

22,487 views • 9 months ago

🚨 NOW YOU RUN A COMPANY WITH ZERO EMPLOYEES Paperclip is a 100% open-source framework (70k+ stars) that makes this possible. Rather than just prompting a model, you hire a CEO, engineers, and a QA reviewer. Every worker is an AI agent, and Paperclip is the Node.js and React control plane that keeps them aligned. Stop chaining messy scripts together and build a living organization: → Stand up a CEO agent to set strategy → Hire engineers and designers via Claude or Codex → Build in an automated QA loop before any ticket closes → Manage the entire portfolio from your phone When an agent slips, you do not rewrite your whole pipeline: you just correct its persona prompt, exactly like coaching a junior hire. It is exactly the kind of tooling the space needs right now. Free, open-source, and self-hosted. Repo link in 🧵↓

🚨 NOW YOU RUN A COMPANY WITH ZERO EMPLOYEES Paperclip is a 100% open-source framework (70k+ stars) that makes this possible. Rather than just prompting a model, you hire a CEO, engineers, and a QA reviewer. Every worker is an AI agent, and Paperclip is the Node.js and React control plane that keeps them aligned. Stop chaining messy scripts together and build a living organization: → Stand up a CEO agent to set strategy → Hire engineers and designers via Claude or Codex → Build in an automated QA loop before any ticket closes → Manage the entire portfolio from your phone When an agent slips, you do not rewrite your whole pipeline: you just correct its persona prompt, exactly like coaching a junior hire. It is exactly the kind of tooling the space needs right now. Free, open-source, and self-hosted. Repo link in 🧵↓

Charly Wargnier

37,174 views • 2 months ago

THIS DEVELOPER USED A 10,000+ STAR OBSIDIAN REPO TO TURN HIS GROWING VAULT INTO A SEARCHABLE AI MEMORY SYSTEM most people keep adding notes until the graph looks impressive but nobody can find the exact context when a real task starts new note → ai summary → entity links → backlinks → graph update → claude retrieves the right 3–5 files instead of scanning the entire vault the system connects projects, decisions, research, and unfinished ideas, so old context resurfaces automatically instead of disappearing inside hundreds of folders he built the workflow around Claudian, an open-source repo with 10,000+ GitHub stars that brings Claude Code directly into Obsidian → bookmark this before your next 1,000 notes become another beautiful graph that your AI still cannot use

THIS DEVELOPER USED A 10,000+ STAR OBSIDIAN REPO TO TURN HIS GROWING VAULT INTO A SEARCHABLE AI MEMORY SYSTEM most people keep adding notes until the graph looks impressive but nobody can find the exact context when a real task starts new note → ai summary → entity links → backlinks → graph update → claude retrieves the right 3–5 files instead of scanning the entire vault the system connects projects, decisions, research, and unfinished ideas, so old context resurfaces automatically instead of disappearing inside hundreds of folders he built the workflow around Claudian, an open-source repo with 10,000+ GitHub stars that brings Claude Code directly into Obsidian → bookmark this before your next 1,000 notes become another beautiful graph that your AI still cannot use

Gipp 🦅

16,393 views • 1 month ago

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

Akshay 🚀

52,426 views • 6 months ago

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them instead

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them instead

Marvin

24,954 views • 2 months ago

SOMEONE TURNED THEIR TEAM'S TASK TRACKER INTO A 3D ISLAND instead of a boring list of tasks, your teams work is a little island that grows as you get stuff done > you assign tasks right in slack, just type who its for, the points, and the due date > finish a task and you get to place a building on the island > get your work rejected and the building collapses into rubble > the rubble stays there forever, so everyone can see it > each new sprint starts a fresh island so over time the island fills up with buildings for all the work your team actually finished, and the rubble is a reminder of what got rejected. its open source, so any team can set it up. way more fun than staring at a to do list all day

SOMEONE TURNED THEIR TEAM'S TASK TRACKER INTO A 3D ISLAND instead of a boring list of tasks, your teams work is a little island that grows as you get stuff done > you assign tasks right in slack, just type who its for, the points, and the due date > finish a task and you get to place a building on the island > get your work rejected and the building collapses into rubble > the rubble stays there forever, so everyone can see it > each new sprint starts a fresh island so over time the island fills up with buildings for all the work your team actually finished, and the rubble is a reminder of what got rejected. its open source, so any team can set it up. way more fun than staring at a to do list all day

Om Patel

12,978 views • 1 month ago

warp code feels like a combination of a cli agent and cursor-style ux design it's a cli that looks like an ide because it gives you: - editor code view - project explorer - one-click to view command output - switch between agent/cli - context/credit spend tracking - task lists - shared context with warp drive there is a learning curve because it's a different workflow, but the agent was top of terminal bench until recently and i can see why would love to see them add: - subagents - an agent sdk - sidebar fonts increasing with cmd +/- not being paid to post this, btw (feel like i have to add that these days 😉) i have been using warp for a long while as a terminal and sometimes agent on the $15/mo plan

warp code feels like a combination of a cli agent and cursor-style ux design it's a cli that looks like an ide because it gives you: - editor code view - project explorer - one-click to view command output - switch between agent/cli - context/credit spend tracking - task lists - shared context with warp drive there is a learning curve because it's a different workflow, but the agent was top of terminal bench until recently and i can see why would love to see them add: - subagents - an agent sdk - sidebar fonts increasing with cmd +/- not being paid to post this, btw (feel like i have to add that these days 😉) i have been using warp for a long while as a terminal and sometimes agent on the $15/mo plan

Ian Nuttall

32,665 views • 10 months ago

Claude Mobile starts the idea... Ghostty finishes it I basically use Claude Mobile as a notepad now. Whenever something comes to mind, I open the app, pick a repo, and ask Claude to start exploring. Then I just let it run while I go on with my day. Later I jump into Claude Desktop and I’m right back in the same session, with context, structure, and a clearer shape of the idea. I tweak a few things to set up the coding phase. Finally, one click to Ghostty (video), open a couple of worktrees, and start working on the PR. IMPORTANT: when you move to Ghostty, it must be the exact same repo you started on mobile, otherwise the --teleport command will fail

Claude Mobile starts the idea... Ghostty finishes it I basically use Claude Mobile as a notepad now. Whenever something comes to mind, I open the app, pick a repo, and ask Claude to start exploring. Then I just let it run while I go on with my day. Later I jump into Claude Desktop and I’m right back in the same session, with context, structure, and a clearer shape of the idea. I tweak a few things to set up the coding phase. Finally, one click to Ghostty (video), open a couple of worktrees, and start working on the PR. IMPORTANT: when you move to Ghostty, it must be the exact same repo you started on mobile, otherwise the --teleport command will fail

Daniel San

67,891 views • 6 months ago

Today we’re introducing Copilot Mode in Edge, our first step in reinventing the browser for the AI age. My favorite feature is multi-tab RAG. You can use Copilot to analyze your open tabs, like I do here with papers our team has published in nature journals over the last year. And there is a lot more to come, including built-in actions so you can delegate tasks as you browse.

Today we’re introducing Copilot Mode in Edge, our first step in reinventing the browser for the AI age. My favorite feature is multi-tab RAG. You can use Copilot to analyze your open tabs, like I do here with papers our team has published in nature journals over the last year. And there is a lot more to come, including built-in actions so you can delegate tasks as you browse.

Satya Nadella

705,330 views • 1 year ago

the so101 + leslider frame i've been playing with the past few weeks wasn't just a random rig i built for fun it's what we at LiveKit built to benchmark and debug our infra (s/o livekit-portal), and today we're open-sourcing it so everyone can reproduce and share coolio results at home here is the github: i know this isn’t the first frame designed for evals, but it’s ours, and it’s open, and it’s with a LeSlider! along with this, we’ve released simulations files (URDF, MJCF, and USD), as well as a sample RL env in MJLab for pick-and-place tasks we want people to have fun, being close to the frontier as much as possible, and we want people to know it shouldn’t take thousands of dollars in equipment to reproduce some of the most amazing results the academic world has to offer personally, I’m going to deploy sim2real and real2sim2real pipelines on this soon, for fun, so look out for that.

the so101 + leslider frame i've been playing with the past few weeks wasn't just a random rig i built for fun it's what we at LiveKit built to benchmark and debug our infra (s/o livekit-portal), and today we're open-sourcing it so everyone can reproduce and share coolio results at home here is the github: i know this isn’t the first frame designed for evals, but it’s ours, and it’s open, and it’s with a LeSlider! along with this, we’ve released simulations files (URDF, MJCF, and USD), as well as a sample RL env in MJLab for pick-and-place tasks we want people to have fun, being close to the frontier as much as possible, and we want people to know it shouldn’t take thousands of dollars in equipment to reproduce some of the most amazing results the academic world has to offer personally, I’m going to deploy sim2real and real2sim2real pipelines on this soon, for fun, so look out for that.

Binh

18,257 views • 1 month ago

It has been an extraordinary run. As I leave the State House for the last time as Governor, I am proud to say we are leaving our children a state that is better than we found it. A New Jersey that is stronger, fairer, and more responsible. To each and every New Jerseyan: It has been the highest honor of my life to serve as your Governor. Thank you for joining me on this journey. Never forget: We’re from Jersey, baby!!

It has been an extraordinary run. As I leave the State House for the last time as Governor, I am proud to say we are leaving our children a state that is better than we found it. A New Jersey that is stronger, fairer, and more responsible. To each and every New Jerseyan: It has been the highest honor of my life to serve as your Governor. Thank you for joining me on this journey. Never forget: We’re from Jersey, baby!!

Governor Phil Murphy

186,224 views • 7 months ago

Rolling out some new interface experiments in Moneybot on Cash App First one: Visual Prompts. We’re trying to move AI beyond chat UI. Chat assumes you know what to ask, then makes you read instead of just showing. Visual Prompts bring together context, visual interface, and actions around what matters most in the moment. A change in spending. An upcoming payment. A chance to save more. Goal is to feel more GUI than chatbot. Will report back what customers think.

Rolling out some new interface experiments in Moneybot on Cash App First one: Visual Prompts. We’re trying to move AI beyond chat UI. Chat assumes you know what to ask, then makes you read instead of just showing. Visual Prompts bring together context, visual interface, and actions around what matters most in the moment. A change in spending. An upcoming payment. A chance to save more. Goal is to feel more GUI than chatbot. Will report back what customers think.

cam worboys

111,902 views • 28 days ago

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓

whoever leaked this has bigger balls than sense Google Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓

Argona

889,913 views • 18 days ago

Introducing fx, a tiny, open, native coding agent from Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑

Introducing fx, a tiny, open, native coding agent from Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑

Vercel Developers

948,088 views • 13 days ago

THIS 38,000-STAR GITHUB REPO TURNS ONE AI AGENT INTO A REAL TEAM THAT CAN BRANCH, VERIFY ITS WORK AND WAIT FOR YOUR APPROVAL most people still run agents as one long chain where every step waits, one failure kills the run and the full workflow starts again Task → Planner → 5 Researchers in Parallel → Skeptic → Writer → Human Gate LangGraph gives every node one job while a shared state carries the findings, decisions and context through the entire system the skeptic can reject an unsupported finding and route the work back before it contaminates the final report, while independent branches keep moving if the run crashes, durable execution resumes from the saved state instead of rebuilding everything, then human-in-the-loop pauses the graph before anything expensive gets sent or published bookmark this repo and watch one prompt turn into an actual org chart for AI agents

THIS 38,000-STAR GITHUB REPO TURNS ONE AI AGENT INTO A REAL TEAM THAT CAN BRANCH, VERIFY ITS WORK AND WAIT FOR YOUR APPROVAL most people still run agents as one long chain where every step waits, one failure kills the run and the full workflow starts again Task → Planner → 5 Researchers in Parallel → Skeptic → Writer → Human Gate LangGraph gives every node one job while a shared state carries the findings, decisions and context through the entire system the skeptic can reject an unsupported finding and route the work back before it contaminates the final report, while independent branches keep moving if the run crashes, durable execution resumes from the saved state instead of rebuilding everything, then human-in-the-loop pauses the graph before anything expensive gets sent or published bookmark this repo and watch one prompt turn into an actual org chart for AI agents

Gipp 🦅

11,524 views • 1 month ago

We built an interactive 3D module to teach kids about what temperature does to water. - You adjust the temperature in real time - You see the impact on the state of water and what's changing at a molecular level - You can unlock two secret states in there if you pass a quick quizz This is the first of a giant series. We're turning the open source Marble App curriculum into a full bank of these interactive lessons. One for each topic kids learn in primary school. If you are a parent or primary school teacher, let us know in comments which module you want to see next. Link to play with the water lab below 👇

We built an interactive 3D module to teach kids about what temperature does to water. - You adjust the temperature in real time - You see the impact on the state of water and what's changing at a molecular level - You can unlock two secret states in there if you pass a quick quizz This is the first of a giant series. We're turning the open source Marble App curriculum into a full bank of these interactive lessons. One for each topic kids learn in primary school. If you are a parent or primary school teacher, let us know in comments which module you want to see next. Link to play with the water lab below 👇

Lionel Mora

118,331 views • 1 month ago

sorry, they just did WHAT someone gave a machine one disease name, the leading cause of blindness in the developed world with 1.5 million americans already in its path, and it came back pointing at a drug that has sat in pharmacies for years under a different label: 551 papers read in 30 minutes against the 294 hours a human would have needed, and the loop that did it is public on GitHub most agent setups answer one question at a time, so the ceiling on the work is the quality of the question you happened to think of this one was handed a single question and wrote the second one itself. turns out that follow-up is where the real find was: a target called ABCA1, upregulated threefold, in an experiment no human ordered i read the whole paper looking for the trick, and the trick is structural. that is the second question, and it is the gap between an assistant and a factory: - hand the loop a field rather than a task: it was given a disease, and choosing the mechanism was part of its job - make it rank before it spends: 151 papers in, ten candidate mechanisms out, scored against each other before anything touched a bench - split reading from judging, so the agent that forms the theory is a different agent from the one grading it - close every cycle on physical reality: the verdict was an experiment, and another model's opinion was never allowed to stand in for one - feed each result back as the next question rather than a log line, which is the step almost nobody builds - search what already passed inspection first: the winner was an approved compound with a safety file already on record - write down what the round learned before opening the next one, so round two starts where round one stopped my read, and i think it is the uncomfortable one: reading was the entire bottleneck in that field, and everybody spent the decade optimising the writing. people ran every physical experiment here, the analysis agent needs a domain expert writing its prompts, and the authors decline to call this the leap it resembles. the thinking got replaced, and the hands did not so the question i cannot answer for my own setup: which step of your loop still stops dead until you sit down and type something bookmark this one. the four parts that turn one model into a line that runs like this, the queue, the rooms, the write permissions and the gate, are built file by file in the piece below ↓

sorry, they just did WHAT someone gave a machine one disease name, the leading cause of blindness in the developed world with 1.5 million americans already in its path, and it came back pointing at a drug that has sat in pharmacies for years under a different label: 551 papers read in 30 minutes against the 294 hours a human would have needed, and the loop that did it is public on GitHub most agent setups answer one question at a time, so the ceiling on the work is the quality of the question you happened to think of this one was handed a single question and wrote the second one itself. turns out that follow-up is where the real find was: a target called ABCA1, upregulated threefold, in an experiment no human ordered i read the whole paper looking for the trick, and the trick is structural. that is the second question, and it is the gap between an assistant and a factory: - hand the loop a field rather than a task: it was given a disease, and choosing the mechanism was part of its job - make it rank before it spends: 151 papers in, ten candidate mechanisms out, scored against each other before anything touched a bench - split reading from judging, so the agent that forms the theory is a different agent from the one grading it - close every cycle on physical reality: the verdict was an experiment, and another model's opinion was never allowed to stand in for one - feed each result back as the next question rather than a log line, which is the step almost nobody builds - search what already passed inspection first: the winner was an approved compound with a safety file already on record - write down what the round learned before opening the next one, so round two starts where round one stopped my read, and i think it is the uncomfortable one: reading was the entire bottleneck in that field, and everybody spent the decade optimising the writing. people ran every physical experiment here, the analysis agent needs a domain expert writing its prompts, and the authors decline to call this the leap it resembles. the thinking got replaced, and the hands did not so the question i cannot answer for my own setup: which step of your loop still stops dead until you sit down and type something bookmark this one. the four parts that turn one model into a line that runs like this, the queue, the rooms, the write permissions and the gate, are built file by file in the piece below ↓

Argona

32,475 views • 23 days ago