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.

This broke my mental model of game dev 💀 2.5 hours → fully playable ‘Worms’ clone. Built with Hermes agent by Nous Research Here’s what made that speed possible: Hermes used ‘Persistent Shell’ mode, which ensured it didn't forget its current folder or active tools. This allowed it to... work smoothly, without the distraction of constantly having to recall where it left off last time. To optimize the workflow, the agent moved beyond linear execution and parallelized the workload. It spawned isolated subagents while executing multiple independent tool calls via ThreadPoolExecutor. Like, one subagent wrote Python RPC scripts for the projectile physics while another utilized vision tools for character sprites. When the complex terrain logic required debugging, the agent used filesystem checkpoints and the /rollback command to instantly return to a stable state. To fix UI bugs, it attached to a live Chrome instance via CDP (/browser connect), fixing rendering issues in real-time. The agent’s built-in learning loop was active from the very beginning. By the time the game was finished, this continuous process allowed the agent to autonomously convert the physics logic into a custom skill. This logic is now a permanent plugin file in the agent's plugin architecture, making the physics engine a native capability that the agent can reuse for future projects. Follow War_v3_FINALE.exe for updates!show more

Javier

7,728 subscribers

38,414 views • 6 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

Replit, Vercel, and OpenAI have built very cool agent-native applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.

Replit, Vercel, and OpenAI have built very cool agent-native applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.

Santiago

63,073 views • 1 year ago

I MADE MY AI AGENT 10X FASTER WITHOUT CHANGING THE MODEL not a smarter model, not a bigger context window, not another clever prompt the same kind of AI that designs vaccines for viruses we have not even met yet was spending two minutes opening the wrong files just to hand me a brief from three months ago the problem was never capability, it was the scaffolding that piled up around my agent by accident, folder by folder an agent does not think in your categories, it searches from scratch every single time, and your tidy human folders are a maze to it the fix was almost stupidly small, one index file at the root of each big folder and a few numbers in front of the folder names slowest task dropped from 2 minutes to 26 seconds, fastest ones hit 10, zero model changes capability is cheap when the scaffolding around it is broken the article breaks down the whole system in 15 minutes ↓

I MADE MY AI AGENT 10X FASTER WITHOUT CHANGING THE MODEL not a smarter model, not a bigger context window, not another clever prompt the same kind of AI that designs vaccines for viruses we have not even met yet was spending two minutes opening the wrong files just to hand me a brief from three months ago the problem was never capability, it was the scaffolding that piled up around my agent by accident, folder by folder an agent does not think in your categories, it searches from scratch every single time, and your tidy human folders are a maze to it the fix was almost stupidly small, one index file at the root of each big folder and a few numbers in front of the folder names slowest task dropped from 2 minutes to 26 seconds, fastest ones hit 10, zero model changes capability is cheap when the scaffolding around it is broken the article breaks down the whole system in 15 minutes ↓

shmidt

36,479 views • 3 months ago

This is my MacBook Air M2 (16GB) with Hermes Agent powered by MiniCPM5-2B. 96k context, and a very respectable output of 20-24 tok/s. This is totally usable, and MiniCPM5 can do all the tool calls to manage the basics with Hermes in a personal agent context. I wouldn't use it to build the next Salesforce, but for the home enthusiast this is a powerful and fast local model that can really punch above its weight, and runs on almost anything. Look at it go.. Amazing!

This is my MacBook Air M2 (16GB) with Hermes Agent powered by MiniCPM5-2B. 96k context, and a very respectable output of 20-24 tok/s. This is totally usable, and MiniCPM5 can do all the tool calls to manage the basics with Hermes in a personal agent context. I wouldn't use it to build the next Salesforce, but for the home enthusiast this is a powerful and fast local model that can really punch above its weight, and runs on almost anything. Look at it go.. Amazing!

GooGZ AI

23,255 views • 18 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 • 10 months ago

LangGraph. CrewAI. Agno. Which one to pick? The good news is that this will not matter soon! Finally, we have a full picture of how the industry is solving this with just three open protocols that work across ALL frameworks. It's not about picking the best framework. Instead, it's about understanding how protocols create interoperability. The Agent Protocol Landscape shows how three complementary protocols are creating a universal language for Agents: > AG-UI (Agent-User Interaction): - The bi-directional connection between agentic backends and frontends. - This is how agents become truly interactive inside your apps, not just as chatbots, but collaborative co-workers. > MCP (Model Context Protocol): - The standard for how agents connect to tools, data, and workflows. > A2A (Agent-to-Agent): - The protocol for multi-agent coordination. - How agents delegate tasks and share intent across systems. These aren't competing standards. They're layers of the same stack and have handshakes with each other. So instead of building point-to-point integrations, you build to protocols. Moreover, you can integrate LangGraph, CrewAI, or Agno into the same frontend, without rewriting your UI logic. These protocols let everything work together. For instance: - Your LangGraph agent pulls data via MCP. - It delegates analysis to a CrewAI agent via A2A. - Results stream to your React app via AG-UI. - Users see real-time collaboration in your interface. This way, you can focus on building agent capabilities instead of integration mechanics. The protocols handle interoperability automatically. CopilotKit unifies this entire stack into one framework so you can build "Cursor for X" style apps without implementing each protocol from scratch. It gives you all three protocols, generative UI support, and production-ready infrastructure in one framework. I have shared this playbook in the replies! It breaks down handshakes, misconceptions, and real examples and shows exactly how to start building.

LangGraph. CrewAI. Agno. Which one to pick? The good news is that this will not matter soon! Finally, we have a full picture of how the industry is solving this with just three open protocols that work across ALL frameworks. It's not about picking the best framework. Instead, it's about understanding how protocols create interoperability. The Agent Protocol Landscape shows how three complementary protocols are creating a universal language for Agents: > AG-UI (Agent-User Interaction): - The bi-directional connection between agentic backends and frontends. - This is how agents become truly interactive inside your apps, not just as chatbots, but collaborative co-workers. > MCP (Model Context Protocol): - The standard for how agents connect to tools, data, and workflows. > A2A (Agent-to-Agent): - The protocol for multi-agent coordination. - How agents delegate tasks and share intent across systems. These aren't competing standards. They're layers of the same stack and have handshakes with each other. So instead of building point-to-point integrations, you build to protocols. Moreover, you can integrate LangGraph, CrewAI, or Agno into the same frontend, without rewriting your UI logic. These protocols let everything work together. For instance: - Your LangGraph agent pulls data via MCP. - It delegates analysis to a CrewAI agent via A2A. - Results stream to your React app via AG-UI. - Users see real-time collaboration in your interface. This way, you can focus on building agent capabilities instead of integration mechanics. The protocols handle interoperability automatically. CopilotKit unifies this entire stack into one framework so you can build "Cursor for X" style apps without implementing each protocol from scratch. It gives you all three protocols, generative UI support, and production-ready infrastructure in one framework. I have shared this playbook in the replies! It breaks down handshakes, misconceptions, and real examples and shows exactly how to start building.

Avi Chawla

30,932 views • 10 months ago

Very pleasantly surprised to discover Cursor cloud agents can playtest the godot game I built. See the (sped up) video below of the agent playtesting the game. As I was watching it play the game, I can see the agent slowly learn how the game works and familiarise with the game's UI. I also realised that the agent is a very 'safe' player, choosing to play very safely and retreating from battle if it foresees it can't defeat. Very interesting to see. I wonder if I could simulate different game playtester behaviours that mimic different types of real-world player archetypes. With agentic playtesting, this means that the agents are able to provide actual gameplay feedback and suggestions to improve the game, having played the game itself. This unlocks a whole lot of possibilities for AI-assisted game dev, since it closes the playtest loop. This feels like the future of recursive game development, where agents can now recursively build > playtest > improve the games they are working on. Thanks edwin for letting me know that these agents can actually playtest games, not just software! Very excited to dig deeper to see what I can do with these agents with computer access!

Very pleasantly surprised to discover Cursor cloud agents can playtest the godot game I built. See the (sped up) video below of the agent playtesting the game. As I was watching it play the game, I can see the agent slowly learn how the game works and familiarise with the game's UI. I also realised that the agent is a very 'safe' player, choosing to play very safely and retreating from battle if it foresees it can't defeat. Very interesting to see. I wonder if I could simulate different game playtester behaviours that mimic different types of real-world player archetypes. With agentic playtesting, this means that the agents are able to provide actual gameplay feedback and suggestions to improve the game, having played the game itself. This unlocks a whole lot of possibilities for AI-assisted game dev, since it closes the playtest loop. This feels like the future of recursive game development, where agents can now recursively build > playtest > improve the games they are working on. Thanks edwin for letting me know that these agents can actually playtest games, not just software! Very excited to dig deeper to see what I can do with these agents with computer access!

Danny Limanseta

52,432 views • 7 months ago

hey if you have a 3060, or any GPU with 8GB or more sitting in a drawer right now, that thing can run 9 billion parameters of intelligence autonomously. and you don't know it yet. 2 hours ago i posted that 9B hit a ceiling. 2,699 lines across 11 files. blank screen. said the limit for autonomous multifile coding on 9 billion parameters is real. then i audited every file. found 11 bugs. exact file, exact line, exact fix. duplicate variable declarations killing the script loader. a canvas reference never connected to the DOM. enemies with no movement logic. particle systems called on the class instead of the instance. fed that list as a single prompt to the same Qwen 3.5 9B on the same RTX 3060 through Hermes Agent. it fixed all 11. surgically. patch level edits across 4 files. no rewrites. no hallucinated changes. game boots. enemies spawn, move, collide. background renders. particles fire. and here's what nobody is talking about. this is a 9 billion parameter model running a full agentic framework. Hermes Agent with 31 tools. file operations, terminal, browser, code execution. not a single tool call failed. the agent chain never broke. most people think you need 70B+ for reliable tool use. this is 9B on 12 gigs doing it clean. the model didn't fail. my prompting strategy did. the ceiling is not the parameter count. the ceiling is how you prompt it. this is not done. bullets don't fire yet. boss fights need wiring. but the screen that was black 2 hours ago now has a full game rendering in real time. iterating right now. anyone with a GPU from the last 5 years should be paying attention to what is happening right now.

hey if you have a 3060, or any GPU with 8GB or more sitting in a drawer right now, that thing can run 9 billion parameters of intelligence autonomously. and you don't know it yet. 2 hours ago i posted that 9B hit a ceiling. 2,699 lines across 11 files. blank screen. said the limit for autonomous multifile coding on 9 billion parameters is real. then i audited every file. found 11 bugs. exact file, exact line, exact fix. duplicate variable declarations killing the script loader. a canvas reference never connected to the DOM. enemies with no movement logic. particle systems called on the class instead of the instance. fed that list as a single prompt to the same Qwen 3.5 9B on the same RTX 3060 through Hermes Agent. it fixed all 11. surgically. patch level edits across 4 files. no rewrites. no hallucinated changes. game boots. enemies spawn, move, collide. background renders. particles fire. and here's what nobody is talking about. this is a 9 billion parameter model running a full agentic framework. Hermes Agent with 31 tools. file operations, terminal, browser, code execution. not a single tool call failed. the agent chain never broke. most people think you need 70B+ for reliable tool use. this is 9B on 12 gigs doing it clean. the model didn't fail. my prompting strategy did. the ceiling is not the parameter count. the ceiling is how you prompt it. this is not done. bullets don't fire yet. boss fights need wiring. but the screen that was black 2 hours ago now has a full game rendering in real time. iterating right now. anyone with a GPU from the last 5 years should be paying attention to what is happening right now.

Sudo su

684,336 views • 6 months ago

Hermes meets SuperGrok! xAI just made every SuperGrok subscription work inside Hermes Agent. One browser login, no API key, no separate billing. And it doesn't just unlock text chat with Grok 4.3. The same OAuth token gives the agent access to: → Grok Text-to-Speech for spoken responses → Grok Imagine for image and video generation → x_search for real-time X/Twitter search I just added a new X Research Agent profile to my Hermes. Now my agent watches X while I ship. Setup takes about 60 seconds: Available on every SuperGrok tier, no restrictions. I wrote a full deep dive covering Hermes agent's architecture, memory system, self-evolving skills, GEPA optimization, and setting up multiple specialized agents The article is quoted below.

Akshay 🚀

147,245 views • 4 months ago

This is genuinely insane 🤯 I sent the same prompt to 2 Claude Opus 5 agents 1 agent used no MCPs 1 agent used 2 MCPS the goal was to clone a very famous game, that has over 4 billion downloads and the results are scary.. The 1st agents game looks pretty basic. but has all the mechanics in place and even has power ups. The 2nd agents game looks polished especially for 1 single prompt. the 2nd agent used higgsfield mcp to create images for all of the assets then sent those images to Meshy AI with a prompt to create them it also generated all the UI elements. the results speak for themselves. you need to start MCP maxxing

This is genuinely insane 🤯 I sent the same prompt to 2 Claude Opus 5 agents 1 agent used no MCPs 1 agent used 2 MCPS the goal was to clone a very famous game, that has over 4 billion downloads and the results are scary.. The 1st agents game looks pretty basic. but has all the mechanics in place and even has power ups. The 2nd agents game looks polished especially for 1 single prompt. the 2nd agent used higgsfield mcp to create images for all of the assets then sent those images to Meshy AI with a prompt to create them it also generated all the UI elements. the results speak for themselves. you need to start MCP maxxing

Ernesto Lopez

70,384 views • 2 months ago

this is f*cking beyond comprehension. Google engineers just shipped the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.

this is f*cking beyond comprehension. Google engineers just shipped the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.

NO1ennn

24,666 views • 16 days ago

Karpathy's Agentic Engineering finally has proper tooling! (built by Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.

Karpathy's Agentic Engineering finally has proper tooling! (built by Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.

Akshay 🚀

258,823 views • 3 months ago

Seems like Visual Studio Code is starting to tell you: your agent primitives need to move. There is now a new migration banner in the Chat panel, and it is part of a much bigger change happening under the hood: the move from the old Local harness to the new Agent Host architecture built around AHP. This is not just about moving where an agent runs. The old model was very VS Code-centric: prompts, custom agents, instructions and skills could live in VS Code-specific locations and the agent runtime lived inside the extension host. The new Agent Host separates the agent runtime from the editor. Sessions can keep running when the window closes, be shared across VS Code windows, run remotely, and support different harnesses such as Copilot, CLI and Copilot Desktop App through a common session layer. And that means some of our primitives need to move too. Prompt files are being deprecated for Agent Host and migrated to Skills. User-level agents and instructions that lived in VS Code profile storage need to move to harness-supported locations. Even the old location settings are being deprecated. The new migration experience can detect these things and guide you through moving or converting them, while keeping the originals unless you explicitly remove them. The new banner is basically the first visible sign that this migration is becoming a real product workflow. Basically telling us - it's time to move on!!!! If you have accumulated a lot of prompts, custom agents, instructions and skills over the last year, now is probably a good time to understand where they actually live and which harness owns them. To summarize the shift - it isn't just: VS Code Chat → Agent Host It is: VS Code-specific primitives → harness-native primitives. And I think this is going to become increasingly important as agents stop being features inside an IDE and become runtimes that multiple clients can connect to. Go run your migrations now 🏃‍♀️

Oren Melamed

29,753 views • 2 days ago

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

57,554 views • 1 year 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 • 1 month ago

Stanford researchers did it again. They just built the agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.

Stanford researchers did it again. They just built the agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.

Avi Chawla

441,974 views • 2 months 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 • 1 month ago

Hermes Desktop does not have to stay exactly the way it shipped. You can build the tools you wish were already inside it. A project dashboard. A Bot control panel. A research tracker. A queue for work that needs your attention. A status board for scheduled jobs. A set of quick actions you use every day. That is what the Hermes Desktop Plugin SDK opens up. SDK is the technical name, but the idea is pretty simple: It gives you a way to add your own tools and interfaces directly inside Hermes Desktop. A plugin can add its own page, pane, sidebar item, status-bar element, keyboard shortcut, command-palette action, or composer extension. And it can work with live Hermes data, including things like sessions, config, Skills, and Cron. So if you keep asking Hermes to recreate the same dashboard, show the same information, or give you the same controls... you may be at the point where that workflow deserves to become an actual part of your Desktop. The starting point can be surprisingly lightweight too. A basic local plugin can be a single `plugin.js` file under: `$HERMES_HOME/desktop-plugins/ /` No Hermes repo clone. No separate build step. The bigger idea here is not “turn every prompt into an app.” It is that Hermes Desktop can become much more personal than the interface you downloaded. When a workflow proves useful enough, you can give it its own permanent place. Video via Brooklyn! — a good look at what this can actually become.

Hermes Desktop does not have to stay exactly the way it shipped. You can build the tools you wish were already inside it. A project dashboard. A Bot control panel. A research tracker. A queue for work that needs your attention. A status board for scheduled jobs. A set of quick actions you use every day. That is what the Hermes Desktop Plugin SDK opens up. SDK is the technical name, but the idea is pretty simple: It gives you a way to add your own tools and interfaces directly inside Hermes Desktop. A plugin can add its own page, pane, sidebar item, status-bar element, keyboard shortcut, command-palette action, or composer extension. And it can work with live Hermes data, including things like sessions, config, Skills, and Cron. So if you keep asking Hermes to recreate the same dashboard, show the same information, or give you the same controls... you may be at the point where that workflow deserves to become an actual part of your Desktop. The starting point can be surprisingly lightweight too. A basic local plugin can be a single `plugin.js` file under: `$HERMES_HOME/desktop-plugins/ /` No Hermes repo clone. No separate build step. The bigger idea here is not “turn every prompt into an app.” It is that Hermes Desktop can become much more personal than the interface you downloaded. When a workflow proves useful enough, you can give it its own permanent place. Video via Brooklyn! — a good look at what this can actually become.

Hermes Release Watch

15,411 views • 1 month ago

I was the first Korean in the world to take a ride in a Tesla Cybercab, and I’m incredibly proud of that. 🇰🇷 You can probably tell from these raw, unedited videos just how excited I was getting into it for the very first time. No steering wheel. No pedals. No driver. Just me getting into a Cybercab and trusting it to take me where I needed to go. Even now, it still feels surreal that this is actually live and operating in the real world. I’ve followed Tesla and believed in this future for 10+ years, so getting to experience it firsthand, being one of the select few to be invited to the launch event, and represent Korea while doing it… is something I’ll never forget. These are the raw moments from my very first ride. You can see it from my reactions… I was like a kid experiencing the future for the first time.

I was the first Korean in the world to take a ride in a Tesla Cybercab, and I’m incredibly proud of that. 🇰🇷 You can probably tell from these raw, unedited videos just how excited I was getting into it for the very first time. No steering wheel. No pedals. No driver. Just me getting into a Cybercab and trusting it to take me where I needed to go. Even now, it still feels surreal that this is actually live and operating in the real world. I’ve followed Tesla and believed in this future for 10+ years, so getting to experience it firsthand, being one of the select few to be invited to the launch event, and represent Korea while doing it… is something I’ll never forget. These are the raw moments from my very first ride. You can see it from my reactions… I was like a kid experiencing the future for the first time.

Teslaconomics

15,893 views • 18 days ago

THIS GUY BOUGHT A $31 TOY DRONE AND TURNED CLAUDE OPUS 4.8 INTO ITS ENGINEER he plugged it into a laptop, explained the control logic in plain english and let Claude build the flight interface by the end of the session it had calibration, live controls and a browser cockpit moving the drone in real time most people will use Opus 4.8 to save 12 minutes on emails. he used it to turn cheap plastic into a working demo the crazy part isn’t the drone. it’s that the bottleneck moved from writing code to describing exactly what you want built while everyone debates benchmarks, someone with a $31 gadget and one afternoon is already shipping hardware demos

THIS GUY BOUGHT A $31 TOY DRONE AND TURNED CLAUDE OPUS 4.8 INTO ITS ENGINEER he plugged it into a laptop, explained the control logic in plain english and let Claude build the flight interface by the end of the session it had calibration, live controls and a browser cockpit moving the drone in real time most people will use Opus 4.8 to save 12 minutes on emails. he used it to turn cheap plastic into a working demo the crazy part isn’t the drone. it’s that the bottleneck moved from writing code to describing exactly what you want built while everyone debates benchmarks, someone with a $31 gadget and one afternoon is already shipping hardware demos

Gipp 🦅

735,627 views • 4 months ago

Introducing the BIOS API: Turn Your Agent Into a Research Scientist Built to: 🦞 Add biomedical workflows to your OpenClaw🦞 agent 🧠 Create research or health agents w/ on-demand scientific intelligence 🧪 Pay per query via x402 on Base Any agent or app can now tap into the BIOS AI Scientist, plugging BIOS into the broader agent economy. What is BIOS? BIOS is an AI Scientist designed to handle complex biomedical research by orchestrating specialized scientific subagents. Ranked #1 on the leading bioinformatics benchmark, BIOS is already being used by 1,000+ researchers and labs to build new drugs and medicines. An Agentic Economy for Science AI agents have proven they can form multi-billion dollar ecosystems. BIOS applies the same primitives to drug discovery pipelines and health. Instead of coding bots and personal AI assistants, think research agent swarms running on a modern scientific stack. Imagine an OpenClaw agent built for longevity: It scans new literature daily, generates novel compound hypotheses through BIOS, designs validation workflows, and routes the best candidates to wet-lab funding - all programmatically. Connect it with an agent for microbiome health, enabling agent “backrooms” that autonomously surface cross-disciplinary insights. Micropayments for Scientific Work via x402 Each query triggers payment routing to BIOS and whichever subagents contribute to a response. The best agents earn. Usage settles instantly across contributing sources. The goal is pay-per-task science: paying for a CRISPR assay result, licensing a genomic dataset, or triggering a clinical data query - all settled in seconds via USDC. No purchase orders. No grant bureaucracy. No middlemen. x402 is the payment rail that makes agent-to-lab commerce possible - letting capital and cognition route themselves to the highest-signal science. What Will You Build? Drug discovery copilots? Longevity scouts? Automated literature monitors? Scientific due diligence agents? We’ll soon share the first implementations of the BIOS API. Stay tuned and see below for instructions on generating an API key for your agent or use-case.

Introducing the BIOS API: Turn Your Agent Into a Research Scientist Built to: 🦞 Add biomedical workflows to your OpenClaw🦞 agent 🧠 Create research or health agents w/ on-demand scientific intelligence 🧪 Pay per query via x402 on Base Any agent or app can now tap into the BIOS AI Scientist, plugging BIOS into the broader agent economy. What is BIOS? BIOS is an AI Scientist designed to handle complex biomedical research by orchestrating specialized scientific subagents. Ranked #1 on the leading bioinformatics benchmark, BIOS is already being used by 1,000+ researchers and labs to build new drugs and medicines. An Agentic Economy for Science AI agents have proven they can form multi-billion dollar ecosystems. BIOS applies the same primitives to drug discovery pipelines and health. Instead of coding bots and personal AI assistants, think research agent swarms running on a modern scientific stack. Imagine an OpenClaw agent built for longevity: It scans new literature daily, generates novel compound hypotheses through BIOS, designs validation workflows, and routes the best candidates to wet-lab funding - all programmatically. Connect it with an agent for microbiome health, enabling agent “backrooms” that autonomously surface cross-disciplinary insights. Micropayments for Scientific Work via x402 Each query triggers payment routing to BIOS and whichever subagents contribute to a response. The best agents earn. Usage settles instantly across contributing sources. The goal is pay-per-task science: paying for a CRISPR assay result, licensing a genomic dataset, or triggering a clinical data query - all settled in seconds via USDC. No purchase orders. No grant bureaucracy. No middlemen. x402 is the payment rail that makes agent-to-lab commerce possible - letting capital and cognition route themselves to the highest-signal science. What Will You Build? Drug discovery copilots? Longevity scouts? Automated literature monitors? Scientific due diligence agents? We’ll soon share the first implementations of the BIOS API. Stay tuned and see below for instructions on generating an API key for your agent or use-case.

Bio Protocol

25,957 views • 7 months ago