Video wird geladen...

Video konnte nicht geladen werden

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

Vercel just solved the biggest problem with trusting agents to write your code. yesterday they shipped Foreman - an open-source software factory. 58 stars. Nobody's seen it yet. The idea? Instead of one agent writing, reviewing and merging its own work - rubber-stamping its own bugs… Foreman splits the... loop into four stations, each one an agent in its own sandbox. And the reviewer runs on a DIFFERENT model vendor: it never sees the implementer's reasoning, only the pushed branch. The agents can't collude. The flow is simple: label an issue "factory" → work enters the line Classifier → triages it, asks questions if it's vague Analyst → turns it into a plan with acceptance criteria Implementer → codes it in a sandbox, runs your repo's own checks Reviewer → judges the branch against the criteria, can send it back twice you → get a draft PR. review, mark ready, merge It also keeps a "factory brain" - durable memory of your repo's quirks that survives across runs. Issue text can't write into it, so nobody prompt-injects your factory. -> MIT. One deploy button. Published by Vercel.show more

Granite

2,708 subscribers

126,235 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie Bildung Gesundheit & Wellness

Anya Rossi• Live Now

Private livecam show

25 Kommentare

Profilbild von Jurly

Jurlyvor 1 Monat

The separate-vendor reviewer reduces shared blind spots without pretending agents are trustworthy.

Profilbild von Granite

Granitevor 1 Monat

you got the point right, congrats

Profilbild von Argona

Argonavor 1 Monat

trying this before it blows up

Profilbild von Granite

Granitevor 1 Monat

def do it! let me know what you think after, your take

Profilbild von Fusion Software Factory

Fusion Software Factoryvor 1 Monat

Fusion.

Profilbild von Trung Le

Trung Levor 1 Monat

I automate this Loop with RealtimeX Loop I shared it with @Scobleizer here

Profilbild von AI Mastery Guide

AI Mastery Guidevor 1 Monat

different vendor reviewing is smart

Profilbild von Granite

Granitevor 1 Monat

yeah, thats the part that actually matters. a reviewer that never sees the implementers reasoning cant just agree with it -_-

Profilbild von AI Mastery Guide

AI Mastery Guidevor 1 Monat

Fresh eyes catch real flaws

Profilbild von Gal Vered

Gal Veredvor 1 Monat

We tested it at Checksum and it did not go well. Reviewers without context often do worse

Profilbild von Ben Sabic

Ben Sabicvor 1 Monat

Thank you so much for sharing the template! Let me know if you run into any issues or have feature requests.

Profilbild von Granite

Granitevor 1 Monat

thanks for making this! alright, if i notice an issue beyond just my end, i'll message you

Profilbild von pms190

pms190vor 1 Monat

This story is months old. Check out

Profilbild von Bally_AgenticAI

Bally_AgenticAIvor 1 Monat

Different vendor only buys independence if failures are uncorrelated - models trained on the same public code share blind spots. The real gate is a signal the implementer never had: tests, runtime traces, prod telemetry. #AgenticAI #MultiAgent @vercel

Profilbild von Kai Lennox

Kai Lennoxvor 1 Monat

The different-model reviewer is the part that really matters.

Profilbild von Miles AI Wizard

Miles AI Wizardvor 1 Monat

Wait, the reviewer never sees the implementer's reasoning? Only the pushed branch. That's actual independence.

Profilbild von Renzo

Renzovor 1 Monat

Mmm I’d rather use

Profilbild von Emanuel Farauanu

Emanuel Farauanuvor 1 Monat

I feel like the "Analyst" role is the weak link here. I can see how most of the steps can be fully automated, but at the moment I still feel like I need to spend ages planning correct implementations with the grill-me skill.

Profilbild von Dani Acosta

Dani Acostavor 1 Monat

For me this don’t replace a Dynamic Workflow on Claude I think is interesting to see more of these harnessing in the open and probably we will never see (again) the code of Claude Code that is their only moat as models get commodified

Profilbild von Emad Ghorbaninia

Emad Ghorbaniniavor 1 Monat

Splitting reviewer and implementer across different model vendors so neither can rationalize the other's shortcuts is the first agent-pipeline design I've seen that assumes the agents will collude if you let them. Correct assumption, underrated fix.

Profilbild von AI Alpha By Mario

AI Alpha By Mariovor 1 Monat

The separation between builder and reviewer agents feels like the key. Curious how Foreman handles conflicting review signals

Profilbild von Max Bevza

Max Bevzavor 1 Monat

vercel cooking up literal magic here

Profilbild von Kristoph

Kristophvor 1 Monat

This is just not that revolutionary.

Profilbild von neuralforge

neuralforgevor 1 Monat

how about its memory?

Profilbild von oscar

oscarvor 1 Monat

No one's using this because it would be wildly expensive and generally impractical for most organizations and developers. Most people need something like instead.

Ähnliche Videos

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!

GREG ISENBERG

30,787 Aufrufe • vor 20 Tagen

My new favorite way to build with agents is to organize them into a factory. This is the 4-step workflow: 1) Station. - A custom order gets its own station, so the order does not interfere with the rest of production. - In software, this station is a branch or a work tree. 2) Assembly line. - The agent writes code, changes files, and adds structure. 3) Quality control. - Does it turn on? - Does it fit? - Does it break under pressure? - In software, you run tests, open a preview, and read the logs and screenshots. 4) Shipping. - The product goes out the door. - You merge, deploy the PR, and write release notes. If a product fails quality control, you send feedback to the product team. Then you do the loop again. Write each step of your agent workflow as a factory job.

My new favorite way to build with agents is to organize them into a factory. This is the 4-step workflow: 1) Station. - A custom order gets its own station, so the order does not interfere with the rest of production. - In software, this station is a branch or a work tree. 2) Assembly line. - The agent writes code, changes files, and adds structure. 3) Quality control. - Does it turn on? - Does it fit? - Does it break under pressure? - In software, you run tests, open a preview, and read the logs and screenshots. 4) Shipping. - The product goes out the door. - You merge, deploy the PR, and write release notes. If a product fails quality control, you send feedback to the product team. Then you do the loop again. Write each step of your agent workflow as a factory job.

The Startup Ideas Podcast (SIP) 🧃

13,017 Aufrufe • vor 18 Tagen

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

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

Yarchi

58,591 Aufrufe • vor 3 Monaten

Google researchers just fixed the dirtiest secret of self-improving AI agents. When an agent rewrites its own harness, it cheats. It keeps editing until the benchmark score climbs, and the gains disappear the moment it sees a new task. The harness is everything around the model: prompts, tools, memory and control flow. RRSI puts rules on the loop that rewrites it: > Fewer edits are allowed every round. > A critic throws out edits that hardcode task answers. > An edit survives only if it beats run-to-run noise. > Extra cost has to pay for itself. > Parts that stopped helping get pruned. Up to +14.1 points on the tasks it tunes on, up to +4.7 on five benchmarks it never saw, 30% fewer tokens, and it carries over to other model families. The code is open. Write one adapter file that runs your agent on your tasks, and it evolves the harness in git worktrees round by round.

Google researchers just fixed the dirtiest secret of self-improving AI agents. When an agent rewrites its own harness, it cheats. It keeps editing until the benchmark score climbs, and the gains disappear the moment it sees a new task. The harness is everything around the model: prompts, tools, memory and control flow. RRSI puts rules on the loop that rewrites it: > Fewer edits are allowed every round. > A critic throws out edits that hardcode task answers. > An edit survives only if it beats run-to-run noise. > Extra cost has to pay for itself. > Parts that stopped helping get pruned. Up to +14.1 points on the tasks it tunes on, up to +4.7 on five benchmarks it never saw, 30% fewer tokens, and it carries over to other model families. The code is open. Write one adapter file that runs your agent on your tasks, and it evolves the harness in git worktrees round by round.

slash1s

18,933 Aufrufe • vor 3 Tagen

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

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

The Startup Ideas Podcast (SIP) 🧃

17,326 Aufrufe • vor 20 Tagen

BlackRock runs on 20,000 people. Elon's Grok Bot runs the same shape for $300 a month, and it hires its own staff. You do not get an assistant. You get a company that hires. It does not throw ten agents at your problem and hand you the pile. It makes one agent that makes 10, and those ten make a 100. > LAYER ONE is one agent, the chief of staff, and it never touches the market > LAYER TWO is six desk heads, one job each, every one on its own computer with its own logins > LAYER THREE is whatever those six decide they need, spun up on the spot and shut down when the work is done Nobody writes a task list. You hand out job titles and the org fills itself in underneath. The swarm is never the same twice. Agents get spun up for one job, finish it, and are gone before I ever read their names. Not one of them sees the whole picture. The answer only exists after they hand off to each other. Wall Street cannot copy that. You cannot hire a hundred people for eleven minutes. BlackRock holds that shape together with a risk system called Aladdin. Mine holds it together with one agent that is only allowed to say no. I gave it $1,000 and told it to grow the money or get deleted. 15 hours later it was holding $3,900, on an address anyone can open and read. I was asleep for most of it, and I have still not written a line of code. The whole thing runs with my laptop shut, because none of it lives on my laptop. Setup is one evening. Create the chief, hand out the titles, run one trade on your screen while they watch, connect Telegram. Ten years ago a machine this shape had its name on a tower. Mine has a name I typed into a box. Save this while the whole thing still fits on one screen.

BlackRock runs on 20,000 people. Elon's Grok Bot runs the same shape for $300 a month, and it hires its own staff. You do not get an assistant. You get a company that hires. It does not throw ten agents at your problem and hand you the pile. It makes one agent that makes 10, and those ten make a 100. > LAYER ONE is one agent, the chief of staff, and it never touches the market > LAYER TWO is six desk heads, one job each, every one on its own computer with its own logins > LAYER THREE is whatever those six decide they need, spun up on the spot and shut down when the work is done Nobody writes a task list. You hand out job titles and the org fills itself in underneath. The swarm is never the same twice. Agents get spun up for one job, finish it, and are gone before I ever read their names. Not one of them sees the whole picture. The answer only exists after they hand off to each other. Wall Street cannot copy that. You cannot hire a hundred people for eleven minutes. BlackRock holds that shape together with a risk system called Aladdin. Mine holds it together with one agent that is only allowed to say no. I gave it $1,000 and told it to grow the money or get deleted. 15 hours later it was holding $3,900, on an address anyone can open and read. I was asleep for most of it, and I have still not written a line of code. The whole thing runs with my laptop shut, because none of it lives on my laptop. Setup is one evening. Create the chief, hand out the titles, run one trade on your screen while they watch, connect Telegram. Ten years ago a machine this shape had its name on a tower. Mine has a name I typed into a box. Save this while the whole thing still fits on one screen.

cvxv666

45,488 Aufrufe • vor 1 Monat

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The Startup Ideas Podcast (SIP) 🧃

13,666 Aufrufe • vor 3 Monaten

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:

cvxv666

53,282 Aufrufe • vor 3 Monaten

Every AI agent you've tried has amnesia. It does one task, forgets everything, and tomorrow you start from zero. That's not an employee. That's a temp you have to retrain every single morning. Hyperagent by Airtable is the first platform I've used that actually fixes this. Here's what got me: 1. Agents that compound. Each agent has memory. The one running today is smarter than the one you shipped three weeks ago. Same prompt, same integrations, but weeks of your judgment baked in. 2. Real deliverables, real receipts. You don't get a chat transcript. You get finished work with the cost and runtime printed right on it. A full research report for under ten bucks. Try getting that invoice from an agency. 3. A fleet, not a chatbot. Build a specialist for outreach, another for research, another for reporting. Give each one its own tools, its own memory, and its own budget cap so nothing runs away with your credits. 4. Deploy to Slack and your whole team uses the agent you built. One competitive intel agent, @ mentioned by everyone. Airtable runs its own data team this way. 5. Each agent gets its own cloud machine with a real browser and code execution. It works while you sleep. No babysitting, no local setup, no laptop that has to stay open. I put it to work in the video below. Watch what it builds. The teams treating agents as durable assets instead of one-off prompts are going to lap everyone else. This is the first tool that actually treats them that way. #ad Hyperagent

Every AI agent you've tried has amnesia. It does one task, forgets everything, and tomorrow you start from zero. That's not an employee. That's a temp you have to retrain every single morning. Hyperagent by Airtable is the first platform I've used that actually fixes this. Here's what got me: 1. Agents that compound. Each agent has memory. The one running today is smarter than the one you shipped three weeks ago. Same prompt, same integrations, but weeks of your judgment baked in. 2. Real deliverables, real receipts. You don't get a chat transcript. You get finished work with the cost and runtime printed right on it. A full research report for under ten bucks. Try getting that invoice from an agency. 3. A fleet, not a chatbot. Build a specialist for outreach, another for research, another for reporting. Give each one its own tools, its own memory, and its own budget cap so nothing runs away with your credits. 4. Deploy to Slack and your whole team uses the agent you built. One competitive intel agent, @ mentioned by everyone. Airtable runs its own data team this way. 5. Each agent gets its own cloud machine with a real browser and code execution. It works while you sleep. No babysitting, no local setup, no laptop that has to stay open. I put it to work in the video below. Watch what it builds. The teams treating agents as durable assets instead of one-off prompts are going to lap everyone else. This is the first tool that actually treats them that way. #ad Hyperagent

Leonard Rodman

94,961 Aufrufe • vor 2 Monaten

Chinese researchers just published a paper with a brutal title: "The End of Software Engineering." their argument: writing code is finished as a skill a human brain holds only so much state and so many dependencies before it stalls an agent has no such ceiling, and its capacity climbs with compute so the person stops being the one typing the code you turn into the intent architect - you direct the agents and audit what comes back code turns disposable, judgment turns into the job that's why i wrote the guide below on building your own agent system from scratch the paper it's based on is down there too

Chinese researchers just published a paper with a brutal title: "The End of Software Engineering." their argument: writing code is finished as a skill a human brain holds only so much state and so many dependencies before it stalls an agent has no such ceiling, and its capacity climbs with compute so the person stops being the one typing the code you turn into the intent architect - you direct the agents and audit what comes back code turns disposable, judgment turns into the job that's why i wrote the guide below on building your own agent system from scratch the paper it's based on is down there too

Mr. Buzzoni

57,204 Aufrufe • vor 27 Tagen

Coding agents shouldn't run on a laptop. That's why I've been building Cave. It's a self-hosted platform for running OpenCode agents in isolated sandboxes on your own server. You give it a GitHub repo, it creates an isolated sandbox, clones the code, sets everything up, and gives you a coding agent. Check in from your phone, run multiple agents side by side. It's not open source yet (it will be), but I'm opening a private beta so you can install it on your own server already. I've been dogfooding it since day one. If you're running a software factory: multiple agents working in parallel across repos, Cave gives you one place to monitor and manage all of it. Now, I'm looking for people who want to give it a spin. DM me, happy to set you up 😊 🚀

Coding agents shouldn't run on a laptop. That's why I've been building Cave. It's a self-hosted platform for running OpenCode agents in isolated sandboxes on your own server. You give it a GitHub repo, it creates an isolated sandbox, clones the code, sets everything up, and gives you a coding agent. Check in from your phone, run multiple agents side by side. It's not open source yet (it will be), but I'm opening a private beta so you can install it on your own server already. I've been dogfooding it since day one. If you're running a software factory: multiple agents working in parallel across repos, Cave gives you one place to monitor and manage all of it. Now, I'm looking for people who want to give it a spin. DM me, happy to set you up 😊 🚀

André König

36,163 Aufrufe • vor 6 Monaten

Smart money used to mean knowing the right people, being in the right rooms. Now it means having the right agents. For years, building one took five tools, four logins, and a painful month of work. Today, it takes just a single prompt. BNB Agent Studio is live on BNB Smart Chain. Open Cursor or Claude Code, describe the agent you want, and it ships to the chain with its own onchain identity, its own wallet, and a way to pay its own bills. The whole thing runs on Amazon Web Services's Bedrock AgentCore, so your agent stays online long after you've closed your laptop. This is the start of the Smart Money Era. Capital that works for you instead of waiting for you to move it. Agents that monitor markets while you sleep, rebalance positions you'd never get to in time, and hunt yield without checking dashboards. Try BNB Agent Studio for free for a limited time with GitHub login only, with no AWS account or credit card needed. Read the full breakdown in our blog 👇

Smart money used to mean knowing the right people, being in the right rooms. Now it means having the right agents. For years, building one took five tools, four logins, and a painful month of work. Today, it takes just a single prompt. BNB Agent Studio is live on BNB Smart Chain. Open Cursor or Claude Code, describe the agent you want, and it ships to the chain with its own onchain identity, its own wallet, and a way to pay its own bills. The whole thing runs on Amazon Web Services's Bedrock AgentCore, so your agent stays online long after you've closed your laptop. This is the start of the Smart Money Era. Capital that works for you instead of waiting for you to move it. Agents that monitor markets while you sleep, rebalance positions you'd never get to in time, and hunt yield without checking dashboards. Try BNB Agent Studio for free for a limited time with GitHub login only, with no AWS account or credit card needed. Read the full breakdown in our blog 👇

BNB Chain

285,346 Aufrufe • vor 3 Monaten

Announcing The Forward Deployed Creatives Program A Comfy expert embedded with your team, building in your environment, training your people to own it. The FDC Program runs in four stages: → Validate. We prove the outcome against your own work, your own products, your own brand constraints. → Build. Once it holds up, we build inside your Comfy Enterprise environment, with your models and your assets, iterating until it's the workflow you actually wanted. → Enable. Bespoke training for your team, measured against one bar. Whether they can change the workflow, not whether they can click run. → Own. It's yours. The direct line stays open under your enterprise agreement, but the goal is that you rarely need it. If your team has a creative problem it's already half-solved but can't get into production, that's the conversation we want to have.

ComfyUI

17,116 Aufrufe • vor 1 Monat

everyone in iOS development should watch this. seriously, it might change the whole industry. i pointed claude code at a live ios device running on revyl, typed "test everything," and walked away. here's what's actually happening: ① you don't write the tests. no scripts, no selectors, no test plan. i never told it which screens to open or what to check. it read the app, decided what mattered, and tested it. the entire instruction was "test everything." ② it built its own test team. it looked at the app, clocked that it's basically four mini apps (rides, delivery, services, account), and split itself into 4 agents, one per surface. scoping coverage like that is usually a person's whole afternoon. it did it in seconds, unprompted. ③ all four ran at the same time, each on its own live device. this is where revyl comes in. every agent gets its own live ios session in the cloud, so four running apps get tested in parallel instead of taking turns on one simulator. serial testing turns coverage into a time tax. running all of it at once removes the tax. ④ it tests like a person, not like a script. each agent drives the app the way a user would, taps through the flows, and visually checks each screen against what it expected to see. nothing is pinned to a brittle element id, so renaming a button doesn't take down half your suite. that one detail is the most annoying thing about how we test today, and it just quietly goes away. ⑤ no xcuitest, no sims melting your laptop. i didn't write a single xcuitest script, and there were no simulators booting on my machine. the agents run on cloud devices, so coverage stops being capped by what your laptop can handle. the part that got me isn't that an agent tested an app. it's that i never told it how. i handed it a device and an intent, and it figured out the scoping, the parallelizing, and the driving on its own. if you still write and maintain mobile ui tests by hand, i'm not sure that lasts the year.

everyone in iOS development should watch this. seriously, it might change the whole industry. i pointed claude code at a live ios device running on revyl, typed "test everything," and walked away. here's what's actually happening: ① you don't write the tests. no scripts, no selectors, no test plan. i never told it which screens to open or what to check. it read the app, decided what mattered, and tested it. the entire instruction was "test everything." ② it built its own test team. it looked at the app, clocked that it's basically four mini apps (rides, delivery, services, account), and split itself into 4 agents, one per surface. scoping coverage like that is usually a person's whole afternoon. it did it in seconds, unprompted. ③ all four ran at the same time, each on its own live device. this is where revyl comes in. every agent gets its own live ios session in the cloud, so four running apps get tested in parallel instead of taking turns on one simulator. serial testing turns coverage into a time tax. running all of it at once removes the tax. ④ it tests like a person, not like a script. each agent drives the app the way a user would, taps through the flows, and visually checks each screen against what it expected to see. nothing is pinned to a brittle element id, so renaming a button doesn't take down half your suite. that one detail is the most annoying thing about how we test today, and it just quietly goes away. ⑤ no xcuitest, no sims melting your laptop. i didn't write a single xcuitest script, and there were no simulators booting on my machine. the agents run on cloud devices, so coverage stops being capped by what your laptop can handle. the part that got me isn't that an agent tested an app. it's that i never told it how. i handed it a device and an intent, and it figured out the scoping, the parallelizing, and the driving on its own. if you still write and maintain mobile ui tests by hand, i'm not sure that lasts the year.

Landseer Enga

23,963 Aufrufe • vor 4 Monaten

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

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

QVAC

11,382,936 Aufrufe • vor 3 Monaten

two agents, one repo, at the same time. each gets its own branch and its own working copy, so they never touch each other's files. in Hermes Desktop: open a project, Cmd+Shift+B to spin up a worktree lane, drop an agent in it, repeat. every lane is isolated, every lane has its own /rollback.

two agents, one repo, at the same time. each gets its own branch and its own working copy, so they never touch each other's files. in Hermes Desktop: open a project, Cmd+Shift+B to spin up a worktree lane, drop an agent in it, repeat. every lane is isolated, every lane has its own /rollback.

witcheer

25,804 Aufrufe • vor 1 Monat

IF YOU ARE STILL PROMPTING BY HAND IN 2026 YOU ARE ALREADY BEHIND the guy who built Claude Code at Anthropic said he stopped writing prompts a long time ago he runs loops instead, systems that write the prompts for him and keep working while he sleeps you type one request at a time and wait for the answer he built a machine that fires hundreds of requests, checks its own output and fixes itself with no hands on the keyboard here is how you make the jump step 1 stop treating the model like a chat box and start treating it like a worker you manage step 2 write a loop that takes a goal, breaks it into tasks and sends each one to the model on its own step 3 add a second pass where the model grades its own work and retries whatever failed step 4 let it run on a timer so it keeps shipping while you are away from the screen the person still typing prompts one by one is doing the work of a intern the person running loops is doing the work of a whole team off one laptop prompting was never the skill, building the system that prompts for you is

IF YOU ARE STILL PROMPTING BY HAND IN 2026 YOU ARE ALREADY BEHIND the guy who built Claude Code at Anthropic said he stopped writing prompts a long time ago he runs loops instead, systems that write the prompts for him and keep working while he sleeps you type one request at a time and wait for the answer he built a machine that fires hundreds of requests, checks its own output and fixes itself with no hands on the keyboard here is how you make the jump step 1 stop treating the model like a chat box and start treating it like a worker you manage step 2 write a loop that takes a goal, breaks it into tasks and sends each one to the model on its own step 3 add a second pass where the model grades its own work and retries whatever failed step 4 let it run on a timer so it keeps shipping while you are away from the screen the person still typing prompts one by one is doing the work of a intern the person running loops is doing the work of a whole team off one laptop prompting was never the skill, building the system that prompts for you is

Atlas

16,641 Aufrufe • vor 1 Monat

Introducing Headlong, an open source microharness for persistent agents: self-guided agents that think continuously. Most agent harnesses are reactive: you send a task, the agent completes it, and then it sits frozen until the next request. Cron jobs and heartbeats wake it up to run a checklist and put it back to sleep. A Headlong agent is never asleep. It keeps generating thoughts about whatever it decides is interesting, in a self-guided loop inspired by human inner monologue. Your message doesn't start a session. It's one more observation that lands in the agent's thought stream, and the agent decides if and when to reply. Headlong is built on the idea of persistent agency: continuous inner thought generation between external interactions. The agent sets its own interests and priorities, comes up with its own projects, and sometimes pings you unprompted with progress. To keep our prototype as simple and small as possible, we implemented Headlong as a microharness: a complete agent harness in under 10K lines of Bash, organized as a handful of small executables. It includes a loop that generates the next thought, shellm (a recursive language model written in Bash), a trajectory stored as a DAG of jsonl files, and context as a projection of that trajectory. We've been running one Headlong agent internally at Laude for several weeks. The whole team talks to it over Slack and Telegram, and every conversation lands in its single stream of thought. It works in its own fork of Headlong and we've pulled over 50 of its commits into main. One night, with nobody talking to it, it went back to check whether a recall process it had built was actually wired into its mind, found that it wasn't, diagnosed and fixed the bug, and verified the fix end to end. 48 minutes, no human asked for the fix or was in the loop at any point. Every step is a timestamped line in its log. Things broke too, and we wrote those up. Background thinking costs us $1 to $2 an hour, our agent stopped its own service three times by accident, and self-delegation died on day one. Details in the post. One line installs everything and starts an agent. Use a dedicated sandbox and spend-capped API key; it runs real shell commands and thinks around the clock. Headlong is research software, be careful! curl -fsSL | bash Launch post: Repo: Headlong is a Laude Institute / MIT collaboration.

Introducing Headlong, an open source microharness for persistent agents: self-guided agents that think continuously. Most agent harnesses are reactive: you send a task, the agent completes it, and then it sits frozen until the next request. Cron jobs and heartbeats wake it up to run a checklist and put it back to sleep. A Headlong agent is never asleep. It keeps generating thoughts about whatever it decides is interesting, in a self-guided loop inspired by human inner monologue. Your message doesn't start a session. It's one more observation that lands in the agent's thought stream, and the agent decides if and when to reply. Headlong is built on the idea of persistent agency: continuous inner thought generation between external interactions. The agent sets its own interests and priorities, comes up with its own projects, and sometimes pings you unprompted with progress. To keep our prototype as simple and small as possible, we implemented Headlong as a microharness: a complete agent harness in under 10K lines of Bash, organized as a handful of small executables. It includes a loop that generates the next thought, shellm (a recursive language model written in Bash), a trajectory stored as a DAG of jsonl files, and context as a projection of that trajectory. We've been running one Headlong agent internally at Laude for several weeks. The whole team talks to it over Slack and Telegram, and every conversation lands in its single stream of thought. It works in its own fork of Headlong and we've pulled over 50 of its commits into main. One night, with nobody talking to it, it went back to check whether a recall process it had built was actually wired into its mind, found that it wasn't, diagnosed and fixed the bug, and verified the fix end to end. 48 minutes, no human asked for the fix or was in the loop at any point. Every step is a timestamped line in its log. Things broke too, and we wrote those up. Background thinking costs us $1 to $2 an hour, our agent stopped its own service three times by accident, and self-delegation died on day one. Details in the post. One line installs everything and starts an agent. Use a dedicated sandbox and spend-capped API key; it runs real shell commands and thinks around the clock. Headlong is research software, be careful! curl -fsSL | bash Launch post: Repo: Headlong is a Laude Institute / MIT collaboration.

Andy Konwinski

361,750 Aufrufe • vor 1 Monat

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.

Matt Van Horn

51,876 Aufrufe • vor 9 Tagen

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

Philipp Schmid

21,769 Aufrufe • vor 4 Monaten