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.

Introducing Software Factory Unified Agent. The Software Factory agent now operates across all modules in the assembly line, rather than one agent per module. Users can move with fluidity retaining their conversation history at each step from requirements, to blueprints, to work orders. Skills and alerts are tagged by... show more

8090

10,246 subscribers

136,482 views • 4 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

7 Comments

Jonathan Yu4 months ago

Super proud of what the team cooked with this one! Let us know what you think

Chris Strobl4 months ago

Nice!

Johnny West4 months ago

👏

Xiayi Sun4 months ago

The strongest case is shared context, permissions, and handoffs around Codex/Claude, making orchestration the value rather than replacing the tools.

80904 months ago

That's the goal!

Trung Le4 months ago

i'm happy with codex and claude, why do i need to switch to 8090?

80904 months ago

We are complementary to those tools. Software Factory brings your team and AI agents (Claude/Codex) into a single system to build software together. It's a multi-player experience where your team defines intent, coordinates execution, and maintains full control, visibility, and auditability over every decision from start to finish in your SDLC.

Related Videos

The data analysis self taught class is here on Selar. It’s $50 per module. It’s actually $100 but I’m doing a promo which makes it $50 All modules are 15 videos each. Different Data are inclusive that you can download and practice to do the assignments as well. Projects for each module. Microsoft Excel module : Power bi module : Python module : SQL module: One on one Consultation:

The data analysis self taught class is here on Selar. It’s $50 per module. It’s actually $100 but I’m doing a promo which makes it $50 All modules are 15 videos each. Different Data are inclusive that you can download and practice to do the assignments as well. Projects for each module. Microsoft Excel module : Power bi module : Python module : SQL module: One on one Consultation:

folowosele adeboye

17,696 views • 1 month ago

Until now, AI agent ran on one machine, and one workflow at a time. A memory-heavy step crashed six hours in, and the run started over. Biomni agent now autonomously decides how many machines it needs, how much CPU and memory each task requires, spins them up, and distributes work across them. It operates like a coordinated team working in parallel, rather than one researcher at a work station. This is the foundation for agent-managed infrastructure.

Until now, AI agent ran on one machine, and one workflow at a time. A memory-heavy step crashed six hours in, and the run started over. Biomni agent now autonomously decides how many machines it needs, how much CPU and memory each task requires, spins them up, and distributes work across them. It operates like a coordinated team working in parallel, rather than one researcher at a work station. This is the foundation for agent-managed infrastructure.

Phylo

10,194 views • 4 months ago

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.

Bret Taylor

1,064,258 views • 6 months ago

You can now use TinyFish in Grok Build. Search, Fetch, Agent, and Browser all under one plugin inside SpaceXAI's coding agent. Give Grok Build a real connection to the live web and let it work across any site from your terminal.

You can now use TinyFish in Grok Build. Search, Fetch, Agent, and Browser all under one plugin inside SpaceXAI's coding agent. Give Grok Build a real connection to the live web and let it work across any site from your terminal.

TinyFish

226,945 views • 2 months ago

RADDBG now allows disambiguating global variable evaluations by compilation unit, as well as module or debug info name, regardless of where your selected thread happens to be. It picks module, debug info, compilation unit, and - for local statics - containing function based on the selected thread's position, but those are no longer required, meaning you can evaluate any global variable, in any module, in any unit, from anywhere.

RADDBG now allows disambiguating global variable evaluations by compilation unit, as well as module or debug info name, regardless of where your selected thread happens to be. It picks module, debug info, compilation unit, and - for local statics - containing function based on the selected thread's position, but those are no longer required, meaning you can evaluate any global variable, in any module, in any unit, from anywhere.

Ryan Fleury

12,670 views • 4 months ago

Ford CEO Jim Farley on why it's so difficult for legacy car companies to get software right & why Tesla’s vertically integrated approach is the right one: “We farmed out all the modules that control the vehicles to our suppliers because we could bid them against each other, so Bosch would do the body control module, someone else would do the seat control module, someone else would do the engine control module. We have about 150 of these modules with semiconductors all through the car. The problem is the software are all written by you know 150 different companies and they don't talk to each other. So even though it says Ford on the front, I actually have to go to Bosch to get permission to change their seat Control software. So even if I had a high-speed modem in the vehicle and and I had the ability to write their software, it's actually their IP and I have 150, we call it the loose Confederation of software providers, 150 completely different software programming languages, you know all the structure of the software is different. It’s millions of code and we can't even understand it all. That's why at Ford we've decided in the second generation product to completely insource electric architecture. To do that you need to write all the software yourself, but just remember car companies have never written software like this, ever, so we're literally writing how the vehicle operates the software to operate the vehicle for the first time ever.” via Everything Electric Show:

Ford CEO Jim Farley on why it's so difficult for legacy car companies to get software right & why Tesla’s vertically integrated approach is the right one: “We farmed out all the modules that control the vehicles to our suppliers because we could bid them against each other, so Bosch would do the body control module, someone else would do the seat control module, someone else would do the engine control module. We have about 150 of these modules with semiconductors all through the car. The problem is the software are all written by you know 150 different companies and they don't talk to each other. So even though it says Ford on the front, I actually have to go to Bosch to get permission to change their seat Control software. So even if I had a high-speed modem in the vehicle and and I had the ability to write their software, it's actually their IP and I have 150, we call it the loose Confederation of software providers, 150 completely different software programming languages, you know all the structure of the software is different. It’s millions of code and we can't even understand it all. That's why at Ford we've decided in the second generation product to completely insource electric architecture. To do that you need to write all the software yourself, but just remember car companies have never written software like this, ever, so we're literally writing how the vehicle operates the software to operate the vehicle for the first time ever.” via Everything Electric Show:

Sawyer Merritt

1,172,994 views • 1 year ago

Max Tynan on the gap nobody else is solving. AI coding tools are single-player by design. One developer, one repo, one prompt. Enterprise software is a team sport. Software Factory is the multiplayer layer. Work Orders run inside Cursor, VS Code, or Claude Code through MCP. Requirements, Blueprints, and Tests stay connected in the Knowledge Graph. Engineers keep their IDE. The team gets a system around it.

Max Tynan on the gap nobody else is solving. AI coding tools are single-player by design. One developer, one repo, one prompt. Enterprise software is a team sport. Software Factory is the multiplayer layer. Work Orders run inside Cursor, VS Code, or Claude Code through MCP. Requirements, Blueprints, and Tests stay connected in the Knowledge Graph. Engineers keep their IDE. The team gets a system around it.

8090

102,280 views • 4 months ago

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 views • 20 days ago

Claude Code now supports agent teams (in research preview) Instead of a single agent working through a task sequentially, a lead agent can delegate to multiple teammates that work in parallel to research, debug, and build while coordinating with each other. Try it out today by enabling agent teams in your settings.json!

Claude Code now supports agent teams (in research preview) Instead of a single agent working through a task sequentially, a lead agent can delegate to multiple teammates that work in parallel to research, debug, and build while coordinating with each other. Try it out today by enabling agent teams in your settings.json!

Lydia Hallie ✨

1,445,914 views • 8 months ago

Lysium is an app I've been building specifically for background agent orchestration. Features: → Mobile-first + cross-platform → Run multiple agents in parallel across repositories → Launch agent-based requests from issues and PRs → Swipe actions for close, merge, create PR, and skip-to-tail workflows → One click agent-powered PR reviews + assessments → One-click agent-powered issue assessments Think of it as a cross-platform control plane for async, agent-driven software delivery (that you can control from anywhere). It's still an experiment, but it's open source and available to try:

Lysium is an app I've been building specifically for background agent orchestration. Features: → Mobile-first + cross-platform → Run multiple agents in parallel across repositories → Launch agent-based requests from issues and PRs → Swipe actions for close, merge, create PR, and skip-to-tail workflows → One click agent-powered PR reviews + assessments → One-click agent-powered issue assessments Think of it as a cross-platform control plane for async, agent-driven software delivery (that you can control from anywhere). It's still an experiment, but it's open source and available to try:

nader dabit

47,584 views • 7 months ago

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

NO1ennn

227,525 views • 2 months ago

Quick test of the new damage model (and reason why I needed combat text for debugging). There is quite a lot to unpack, if you won't read this, I won't blame you. Armor penetration is now a thing, and AP/APHE projectiles can exist. A new module system is in place, module shapes and their hitzones are decoupled from hull parts. Hullparts (including parts in armor layers) can have a variable armor rating. Shooting at complex vehicles with APxx ammunition can now yield various results. Ranging from surface hits (white) to module/critical hits (red), Internal hits (penetrating through the hull layer but missing a module) are displayed in yellow. Piercing damage itself is cyan. Modules can now be destroyed, disabling or losing ability modules, defensive fields, or damaging propulsion systems can now happen. Destruction of some modules can also result in quite volatile reactions (we will take a look at that next time). Hence, understanding the layout of your target, its armor layers, and module positions can be greatly beneficial. Energy projectiles can mirror this behavior. The difference is that piercing damage from ballistic projectiles is always kinetic, while for energy projectiles, it's a percentage of their energy pattern. There is a bug in color of ricochet damage numbers, I am aware of it. #Precursor #pixelart #gamedev #indiegame

Quick test of the new damage model (and reason why I needed combat text for debugging). There is quite a lot to unpack, if you won't read this, I won't blame you. Armor penetration is now a thing, and AP/APHE projectiles can exist. A new module system is in place, module shapes and their hitzones are decoupled from hull parts. Hullparts (including parts in armor layers) can have a variable armor rating. Shooting at complex vehicles with APxx ammunition can now yield various results. Ranging from surface hits (white) to module/critical hits (red), Internal hits (penetrating through the hull layer but missing a module) are displayed in yellow. Piercing damage itself is cyan. Modules can now be destroyed, disabling or losing ability modules, defensive fields, or damaging propulsion systems can now happen. Destruction of some modules can also result in quite volatile reactions (we will take a look at that next time). Hence, understanding the layout of your target, its armor layers, and module positions can be greatly beneficial. Energy projectiles can mirror this behavior. The difference is that piercing damage from ballistic projectiles is always kinetic, while for energy projectiles, it's a percentage of their energy pattern. There is a bug in color of ricochet damage numbers, I am aware of it. #Precursor #pixelart #gamedev #indiegame

Jan Orszulik

24,542 views • 2 years ago

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 views • 18 days ago

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

Hermes Release Watch

68,830 views • 1 month ago

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,401 views • 8 months ago

we're back with more software factory alpha on the 🦄 AI That Works show - Vaibhav Gupta and I teamed up with - Tyler Brown - discussed how they run a discuss/do/compound loop in their factory, with Linear as the frontend and all agent sessions running on mac minis - cole murray sharing tales from the trenches rolling out the OSS OpenInspect factory to teams of up to 500 engineers in the enterprises super fun time - catch us every week at 10:15am PT on X and on

we're back with more software factory alpha on the 🦄 AI That Works show - Vaibhav Gupta and I teamed up with - Tyler Brown - discussed how they run a discuss/do/compound loop in their factory, with Linear as the frontend and all agent sessions running on mac minis - cole murray sharing tales from the trenches rolling out the OSS OpenInspect factory to teams of up to 500 engineers in the enterprises super fun time - catch us every week at 10:15am PT on X and on

dex

10,982 views • 23 days ago

starting today Julius can go beyond just answering your questions, now it can spin up browser sessions and take actions across the web using our new browser agent we're pumped to be partnering with Browserbase and Paul Klein IV to bring this capability to our users browser agent in Julius is completely free this week. give it a try!

starting today Julius can go beyond just answering your questions, now it can spin up browser sessions and take actions across the web using our new browser agent we're pumped to be partnering with Browserbase and Paul Klein IV to bring this capability to our users browser agent in Julius is completely free this week. give it a try!

rahul

42,379 views • 2 months ago

Introducing Skills in SciSpace Agent. Specialized modes built for specific research workflows. Describe the task, and the right workflow activates automatically. Yes, the right Skill gets loaded based on what you need. Built to simplify multi-step research work and reduce friction around execution. Skills are now live. Try it inside SciSpace Agent.

Introducing Skills in SciSpace Agent. Specialized modes built for specific research workflows. Describe the task, and the right workflow activates automatically. Yes, the right Skill gets loaded based on what you need. Built to simplify multi-step research work and reduce friction around execution. Skills are now live. Try it inside SciSpace Agent.

SciSpace

43,422 views • 7 months ago

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.

Akshay 🚀

119,319 views • 11 days ago

It doesn’t matter how fast your code is generated if the requirements are unclear. Shit in == shit out. That’s why we designed Software Factory as a discipline, not as a convenience tool. Our agents scrutinize your requirements and designs so that when you pass that context to a coding agent, it delivers as expected. Try it here:

It doesn’t matter how fast your code is generated if the requirements are unclear. Shit in == shit out. That’s why we designed Software Factory as a discipline, not as a convenience tool. Our agents scrutinize your requirements and designs so that when you pass that context to a coding agent, it delivers as expected. Try it here:

Chamath Palihapitiya

305,609 views • 8 months ago