Загрузка видео...

Не удалось загрузить видео

На главную

My real dev stack isn’t just tools for coding. It’s also tools for not getting distracted. Coding: Cursor Tasks: Linear Terminal: Warp Deploy: GitHub Staying updated: one curated dev feed before I start work Everything else got removed quietly over time. No big switch. Just fewer decisions every morning....

Onil_coder's profile picture

Onil Coder

23,767 subscribers

18,451 просмотров • 5 месяцев назад •via X (Twitter)

ОбразованиеЗдоровье и велнесНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Here’s a fun one: the AI developer tools we shipped for Quest a few weeks ago also work on Portal devices! So if you have one, it’s now also a dev kit. Describe an app, deploy over USB. Here’s what I built for my Portal, a centralized home hub where I can see and control our smart devices.
1:25

Here’s a fun one: the AI developer tools we shipped for Quest a few weeks ago also work on Portal devices! So if you have one, it’s now also a dev kit. Describe an app, deploy over USB. Here’s what I built for my Portal, a centralized home hub where I can see and control our smart devices.

Boz

17,749 просмотров • 4 месяцев назад

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵
0:34

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

Hasan

50,678 просмотров • 2 месяцев назад

Everyone’s quietly switching to this… and nobody’s talking about it properly yet. Someone built a 25MB Rust desktop app that packs 7 dev tools in one window. No setup drama. No heavy installs. No waiting. Just open it → and everything is already there. It’s called Clauge (open-source, cross-platform). And the insane part? It has a sub-second cold start. While we’re used to: • Electron apps eating RAM • 10-second startup delays • 5 different tools for 5 simple tasks People are now literally moving to a single lightweight window that does it all. And once you try it, the weird feeling is: “Why was this ever heavy in the first place?” Because clearly, the future dev stack isn’t getting bigger… it’s getting smaller, faster, and tighter.
2:52

Everyone’s quietly switching to this… and nobody’s talking about it properly yet. Someone built a 25MB Rust desktop app that packs 7 dev tools in one window. No setup drama. No heavy installs. No waiting. Just open it → and everything is already there. It’s called Clauge (open-source, cross-platform). And the insane part? It has a sub-second cold start. While we’re used to: • Electron apps eating RAM • 10-second startup delays • 5 different tools for 5 simple tasks People are now literally moving to a single lightweight window that does it all. And once you try it, the weird feeling is: “Why was this ever heavy in the first place?” Because clearly, the future dev stack isn’t getting bigger… it’s getting smaller, faster, and tighter.

divyansh tiwari

30,408 просмотров • 4 месяцев назад

The mindset shift that changed the way I looked at the world: “I’m going to build my own tools” I've automated more daily workflow in the past 12 months than I have my entire career “You can build your own things that other people can use. Once you learn that, you'll never be the same again.” - Steve Jobs "Coding is dead" - Said no one serious The secret wasn’t running away from code No! The opposite. I dove head first into new tools (Cursor, v0, LangSmith, OpenAI, Anthropic, etc.) As the CEO of Cursor puts it, we are entering the golden age of “delight concentration” We can now be creative instead of technical. The friction to building your own tools is literally just a prompt away (Anthropic Artifacts). For custom tools, the barrier to entry is mind-boggling low. Tools like Cursor, v0, shadcn, LangChain and Vercel allow you to build, deploy and share what matters to YOU faster than ever It’s no longer skill level that's holding you back, it’s just your desire to take a step forward
1:02

The mindset shift that changed the way I looked at the world: “I’m going to build my own tools” I've automated more daily workflow in the past 12 months than I have my entire career “You can build your own things that other people can use. Once you learn that, you'll never be the same again.” - Steve Jobs "Coding is dead" - Said no one serious The secret wasn’t running away from code No! The opposite. I dove head first into new tools (Cursor, v0, LangSmith, OpenAI, Anthropic, etc.) As the CEO of Cursor puts it, we are entering the golden age of “delight concentration” We can now be creative instead of technical. The friction to building your own tools is literally just a prompt away (Anthropic Artifacts). For custom tools, the barrier to entry is mind-boggling low. Tools like Cursor, v0, shadcn, LangChain and Vercel allow you to build, deploy and share what matters to YOU faster than ever It’s no longer skill level that's holding you back, it’s just your desire to take a step forward

Greg Kamradt

117,317 просмотров • 2 лет назад

AntiGravity just became 10x more powerful. And 99% of users have no idea. Here's what you can actually do with it: → Switch between free APIs (Opus, Sonnet, Claude) → Generate images with Google's Nano Banana → Connect MCP servers directly to your projects → Use Claude Code inside the terminal for better UI → Deploy apps to Netlify in one click → Pull NotebookLM content into your builds No paid APIs. No limits. Just stack free tools. Save this video, you'll never use it the same way again. Want the SOP? DM me. 💬
12:32

AntiGravity just became 10x more powerful. And 99% of users have no idea. Here's what you can actually do with it: → Switch between free APIs (Opus, Sonnet, Claude) → Generate images with Google's Nano Banana → Connect MCP servers directly to your projects → Use Claude Code inside the terminal for better UI → Deploy apps to Netlify in one click → Pull NotebookLM content into your builds No paid APIs. No limits. Just stack free tools. Save this video, you'll never use it the same way again. Want the SOP? DM me. 💬

Julian Goldie SEO

98,318 просмотров • 9 месяцев назад

Imagine a computer where you don’t need to learn 10 apps to get work done. You just tell it what you want, and it adapts to how you work. I tested Happycapy with a real use case and created an image and a video. No coding, no complex software. Do this: - Build automations that run on schedule - Deploy agent teams that work for you AI molds how you work, not the other way around. If you can use a computer, you can make anything happen. Start your first Automation and Agent teams today.
0:24

Imagine a computer where you don’t need to learn 10 apps to get work done. You just tell it what you want, and it adapts to how you work. I tested Happycapy with a real use case and created an image and a video. No coding, no complex software. Do this: - Build automations that run on schedule - Deploy agent teams that work for you AI molds how you work, not the other way around. If you can use a computer, you can make anything happen. Start your first Automation and Agent teams today.

Aaliya

17,042 просмотров • 8 месяцев назад

I built Quill as a universal voice layer for macOS using Grok's speech-to-text The idea is stupidly simple: STT is insanely good now... why would you want to type when you can just talk? Quill listens in real time and drops the words directly wherever your cursor is... X, email, docs, coding tools, basically any app on your Mac It also opens Grok Build with a single "Open Grok" command No need to switch windows, copy-paste, or stop what you're doing just to type If you're building, coding, writing, researching, or simply spend a lot of time on your Mac, you stop thinking about typing and just focus on what you actually want to say or build It's real-time, works instantly, and it's included with your SuperGrok subscription This is literally a game-changer. Try it once, you'll know
1:29

I built Quill as a universal voice layer for macOS using Grok's speech-to-text The idea is stupidly simple: STT is insanely good now... why would you want to type when you can just talk? Quill listens in real time and drops the words directly wherever your cursor is... X, email, docs, coding tools, basically any app on your Mac It also opens Grok Build with a single "Open Grok" command No need to switch windows, copy-paste, or stop what you're doing just to type If you're building, coding, writing, researching, or simply spend a lot of time on your Mac, you stop thinking about typing and just focus on what you actually want to say or build It's real-time, works instantly, and it's included with your SuperGrok subscription This is literally a game-changer. Try it once, you'll know

X Freeze

85,231 просмотров • 2 месяцев назад

ex-Apple engineer gave Grok 4.6 two jobs inside Cursor, went to sleep, and opened the results live the next morning: no babysitting, no checking every generation, just a model left running on real work for hours. • 00:42 - reveal the website Grok redesigned overnight • 23:21 - go from a voice prompt to a full software stack • 45:43 - inspect the generated code + architecture • 01:21:26 - Grok 4.6 vs Opus 5 • 01:46:31 - live PR + Cloud Agent workflow Most coding demos test an AI for 5 minutes. This tests the thing that matters for agents: can the model keep working when you stop watching it? SpaceXAI built Grok 4.6 specifically around longer-running agent tasks, coding and more ambitious visual work. The endgame isn’t prompting faster. It’s giving an agent a job at night and reviewing finished work in the morning. Worth watching before you choose which model runs your overnight agent loops.
2:27:56

ex-Apple engineer gave Grok 4.6 two jobs inside Cursor, went to sleep, and opened the results live the next morning: no babysitting, no checking every generation, just a model left running on real work for hours. • 00:42 - reveal the website Grok redesigned overnight • 23:21 - go from a voice prompt to a full software stack • 45:43 - inspect the generated code + architecture • 01:21:26 - Grok 4.6 vs Opus 5 • 01:46:31 - live PR + Cloud Agent workflow Most coding demos test an AI for 5 minutes. This tests the thing that matters for agents: can the model keep working when you stop watching it? SpaceXAI built Grok 4.6 specifically around longer-running agent tasks, coding and more ambitious visual work. The endgame isn’t prompting faster. It’s giving an agent a job at night and reviewing finished work in the morning. Worth watching before you choose which model runs your overnight agent loops.

Morlex

5,276,863 просмотров • 1 месяц назад

Grok Build for Windows. Your terminal just got a dev teammate. Plans, writes, runs, debugs. Not suggestions. Execution. Multi-agent system. Arena mode ranking outputs. This is real coding inside PowerShell. Set it up on Windows: * Open PowerShell - run as Administrator * Install it - paste the command irm | iex * Go to your project - cd into your repo * Run grok - launch the CLI * Sign in - one-time login with SuperGrok * Start prompting - build, fix, refactor * Let agents run - parallel work, less waiting * Review outputs - diffs, rankings, results Windows dev flow. No excuses. xAI Grok
1:16

Grok Build for Windows. Your terminal just got a dev teammate. Plans, writes, runs, debugs. Not suggestions. Execution. Multi-agent system. Arena mode ranking outputs. This is real coding inside PowerShell. Set it up on Windows: * Open PowerShell - run as Administrator * Install it - paste the command irm | iex * Go to your project - cd into your repo * Run grok - launch the CLI * Sign in - one-time login with SuperGrok * Start prompting - build, fix, refactor * Let agents run - parallel work, less waiting * Review outputs - diffs, rankings, results Windows dev flow. No excuses. xAI Grok

Mario Nawfal

98,671 просмотров • 4 месяцев назад

Free GPT-5.6 Sol/Terra/Luna + Claude Sonnet 4.6 + a full IDE one code editor just dropped a 14-day Pro trial with popular AI models ( no card required, no BS ) what you get: - GPT-5.6 Sol, Terra, Luna (full family) - Claude Sonnet 4.6 - two weeks of real coding - native IDE built in Rust (10x faster than VS Code) - multiplayer coding + native AI integration how to get: 1. go to zed(.)dev, sign in via GitHub (account must be 1+ month old) 2. click Pricing, select Pro, hit "Start Trial Now" 3. download their IDE 4. open a project -> click the star icon bottom-left -> pick your model in other words, you get a full-featured IDE with leading AI tools that work for free for 14 days - all for $0. based on the tests I've run, I'd say the speed and ease of use are really great - on par with Cursor. btw I recently wrote a full guide on ways to pay $0 for every subscription you have - this is just one of them worth to read:
0:26

Free GPT-5.6 Sol/Terra/Luna + Claude Sonnet 4.6 + a full IDE one code editor just dropped a 14-day Pro trial with popular AI models ( no card required, no BS ) what you get: - GPT-5.6 Sol, Terra, Luna (full family) - Claude Sonnet 4.6 - two weeks of real coding - native IDE built in Rust (10x faster than VS Code) - multiplayer coding + native AI integration how to get: 1. go to zed(.)dev, sign in via GitHub (account must be 1+ month old) 2. click Pricing, select Pro, hit "Start Trial Now" 3. download their IDE 4. open a project -> click the star icon bottom-left -> pick your model in other words, you get a full-featured IDE with leading AI tools that work for free for 14 days - all for $0. based on the tests I've run, I'd say the speed and ease of use are really great - on par with Cursor. btw I recently wrote a full guide on ways to pay $0 for every subscription you have - this is just one of them worth to read:

kaize

35,844 просмотров • 2 месяцев назад

Imagine this for a second. Everywhere you go, everything you do there’s a digital version of you quietly following along. Not just your name or your date of birth, but your habits, your movements, what you buy, where you travel, even who you spend time with. Now, we’re being told it’s a good idea to bundle all of that into a single digital ID. Sounds convenient, right? But convenience has a cost and it’s usually paid in control. Think of a digital ID like putting all your keys your house key, your car key, your office key onto one single keycard. Lose it, and you’re locked out of everything. But worse than losing it is someone else getting hold of it. One breach, one hack, one system failure… and suddenly your entire identity isn’t just expose it’s vulnerable. Now imagine that system isn’t just used to prove who you are, but also to decide what you can do. Maybe it starts small. You need it to access services, to travel, to work. Fair enough. But over time, it can quietly become a gatekeeper. If something goes wrong an error, a disagreement, even a false flag you could find yourself locked out of basic parts of life, with no easy way to fix it. And here’s the thing people don’t always realise: once a system like that is built, it doesn’t stay limited. It expands. New features get added. New rules come in. What starts as “optional” can quickly become unavoidable. It’s not about being paranoid it’s about understanding human systems. Power tends to grow, not shrink. In everyday terms, scrapping digital ID isn’t about rejecting technology. It’s about keeping balance. It’s about making sure no single system has too much control over who you are and what you’re allowed to do. Because your identity isn’t just data. It’s yours. And once you hand over the keys completely, it’s very hard to get them back. Richie Taylor Scrap Digital ID Sat 25 April 2pm The Senedd Cardiff And London Belfast Edinburgh #notodigitalid #together
1:59

Imagine this for a second. Everywhere you go, everything you do there’s a digital version of you quietly following along. Not just your name or your date of birth, but your habits, your movements, what you buy, where you travel, even who you spend time with. Now, we’re being told it’s a good idea to bundle all of that into a single digital ID. Sounds convenient, right? But convenience has a cost and it’s usually paid in control. Think of a digital ID like putting all your keys your house key, your car key, your office key onto one single keycard. Lose it, and you’re locked out of everything. But worse than losing it is someone else getting hold of it. One breach, one hack, one system failure… and suddenly your entire identity isn’t just expose it’s vulnerable. Now imagine that system isn’t just used to prove who you are, but also to decide what you can do. Maybe it starts small. You need it to access services, to travel, to work. Fair enough. But over time, it can quietly become a gatekeeper. If something goes wrong an error, a disagreement, even a false flag you could find yourself locked out of basic parts of life, with no easy way to fix it. And here’s the thing people don’t always realise: once a system like that is built, it doesn’t stay limited. It expands. New features get added. New rules come in. What starts as “optional” can quickly become unavoidable. It’s not about being paranoid it’s about understanding human systems. Power tends to grow, not shrink. In everyday terms, scrapping digital ID isn’t about rejecting technology. It’s about keeping balance. It’s about making sure no single system has too much control over who you are and what you’re allowed to do. Because your identity isn’t just data. It’s yours. And once you hand over the keys completely, it’s very hard to get them back. Richie Taylor Scrap Digital ID Sat 25 April 2pm The Senedd Cardiff And London Belfast Edinburgh #notodigitalid #together

Alan D Miller

16,198 просмотров • 6 месяцев назад

Most coding agents can complete the task. But here’s the real question: Would you actually merge that code? Cosine didn’t just ship a feature. They’re doubling down on a bigger idea: One agent across every surface developers use. CLI Desktop VS Code Cloud Same runtime. Same system. No context switching. What stands out is the philosophy. Cosine is opinionated by design. Not trying to be minimal. Not trying to be “just a chatbot.” It’s built for real engineering workflows: → Plan → Execute → Review → Scale → Parallel work with Swarm → Remote agents when one machine isn’t enough → Nothing merges without review Most tools today still feel stitched together. Cosine is pushing toward one unified system instead. And an important detail a lot of people will care about: You don’t need to switch models or tools. You can plug in your existing subscriptions like ChatGPT, GitHub Copilot, or Claude. Model agnostic by design. No lock-in. This update feels less like a feature drop… and more like a statement: coding agents shouldn’t live in chat windows. they should operate across your entire workflow. Built for engineers with taste. If you care about control, visibility, and code quality this direction is worth paying attention to. Explore what’s new →
1:09

Most coding agents can complete the task. But here’s the real question: Would you actually merge that code? Cosine didn’t just ship a feature. They’re doubling down on a bigger idea: One agent across every surface developers use. CLI Desktop VS Code Cloud Same runtime. Same system. No context switching. What stands out is the philosophy. Cosine is opinionated by design. Not trying to be minimal. Not trying to be “just a chatbot.” It’s built for real engineering workflows: → Plan → Execute → Review → Scale → Parallel work with Swarm → Remote agents when one machine isn’t enough → Nothing merges without review Most tools today still feel stitched together. Cosine is pushing toward one unified system instead. And an important detail a lot of people will care about: You don’t need to switch models or tools. You can plug in your existing subscriptions like ChatGPT, GitHub Copilot, or Claude. Model agnostic by design. No lock-in. This update feels less like a feature drop… and more like a statement: coding agents shouldn’t live in chat windows. they should operate across your entire workflow. Built for engineers with taste. If you care about control, visibility, and code quality this direction is worth paying attention to. Explore what’s new →

Md Riyazuddin

12,203 просмотров • 6 месяцев назад

If you use Cursor for coding, Claude Code for debugging, and local agents for automation, you almost certainly have a context problem. Every tool acts like an isolated employee. One assistant forgets what the other just learned. The biggest bottleneck in multi-agent workflows right now isn’t reasoning. It’s collective amnesia, combined with zero communication between agents. Memmy just launched a smart fix for this: a local, cross-agent memory layer. Instead of re-pasting your context everywhere, Memmy gives your stack a shared memory hub: → accumulate knowledge once, then use it across Cursor, Codex, and OpenClaw → automatically scan and import your existing agent history, so you don’t have to start from zero → keep your memory local, while model usage depends on your chosen provider or BYOK setup And it isn’t just a memory plugin. It’s a complete personal AI runtime with both MCP and a CLI. Memmy officially launched on Product Hunt, and the team is giving early users experiencing context fragmentation a free trial with 2M GPT tokens. Check it out and support the team with an upvote: → Best part? It’s also open-source for devs who want to build their own agents 🔥 Repo in 🧵↓
3:29

If you use Cursor for coding, Claude Code for debugging, and local agents for automation, you almost certainly have a context problem. Every tool acts like an isolated employee. One assistant forgets what the other just learned. The biggest bottleneck in multi-agent workflows right now isn’t reasoning. It’s collective amnesia, combined with zero communication between agents. Memmy just launched a smart fix for this: a local, cross-agent memory layer. Instead of re-pasting your context everywhere, Memmy gives your stack a shared memory hub: → accumulate knowledge once, then use it across Cursor, Codex, and OpenClaw → automatically scan and import your existing agent history, so you don’t have to start from zero → keep your memory local, while model usage depends on your chosen provider or BYOK setup And it isn’t just a memory plugin. It’s a complete personal AI runtime with both MCP and a CLI. Memmy officially launched on Product Hunt, and the team is giving early users experiencing context fragmentation a free trial with 2M GPT tokens. Check it out and support the team with an upvote: → Best part? It’s also open-source for devs who want to build their own agents 🔥 Repo in 🧵↓

Charly Wargnier

203,456 просмотров • 2 месяцев назад

•New this week: Canvas in AI Mode gives you a dynamic space to organize your plans and projects over time, and now it’s available to everyone in the US! Plus, we’re adding support for coding & creative writing tasks, so you can bring even more ideas to life with custom dashboards or interactive tools. My current favorite use case: planning summer camps for my kids in SF. It’s a logistical nightmare 😅 but this year Canvas made life a little easier. I built my personal summer camp app directly in Google Search - from a single prompt to working prototype in just seconds!
0:55

•New this week: Canvas in AI Mode gives you a dynamic space to organize your plans and projects over time, and now it’s available to everyone in the US! Plus, we’re adding support for coding & creative writing tasks, so you can bring even more ideas to life with custom dashboards or interactive tools. My current favorite use case: planning summer camps for my kids in SF. It’s a logistical nightmare 😅 but this year Canvas made life a little easier. I built my personal summer camp app directly in Google Search - from a single prompt to working prototype in just seconds!

Rose Yao

35,271 просмотров • 7 месяцев назад

What if I told you there’s a powerful drug that can transform your health without a single side effect? That drug is not in a pill—it’s in your kitchen. Food isn’t just calories—it’s a molecular signal that programs your biology in real time. Every bite you take sends information to your cells, influencing everything from gene expression to hormone balance, brain chemistry, and immune function. By making thoughtful food choices, you’re leveraging one of the most powerful tools we have in medicine. This drug is faster, cheaper, and more effective than any drug we’ve ever discovered. Will you utilize it?
0:46

What if I told you there’s a powerful drug that can transform your health without a single side effect? That drug is not in a pill—it’s in your kitchen. Food isn’t just calories—it’s a molecular signal that programs your biology in real time. Every bite you take sends information to your cells, influencing everything from gene expression to hormone balance, brain chemistry, and immune function. By making thoughtful food choices, you’re leveraging one of the most powerful tools we have in medicine. This drug is faster, cheaper, and more effective than any drug we’ve ever discovered. Will you utilize it?

Mark Hyman, M.D.

21,994 просмотров • 6 месяцев назад

I gave Claude Code, Codex, and Cursor a self-improving, shared MEMORY. Now my coding agents learn from each other, and their knowledge follows me wherever I work. Coding agents work in silos. Your corrections in Cursor don't carry over to Claude Code, and skills built in Codex don't automatically transfer to other harnesses. So switching tools often means starting from scratch. What if every coding agent could learn from everything you've already done? I invited Justin D'Souza, co-founder of Asymptote Labs, to show me how to make this possible with Beacon, a 100% open-source memory layer for coding agents. We set it up live, explored real coding sessions, and watched Beacon turn past work into reusable knowledge. Here's what I learned: 1. One memory layer for 20+ coding agents. Beacon captures activity across Claude Code, Cursor, Codex, and 20+ harnesses using OpenTelemetry, hooks, and local session files. Everything gets normalized into a single format, regardless of which agent you're using. 2. Your entire coding history becomes searchable. Every prompt, tool call, command, file change, and response is captured in a structured trace. Instead of losing valuable context when a session ends, you build a searchable history of everything your agents have done. 3. Switch agents without starting over. Hit your usage limit in Cursor? Open Claude Code and ask it to continue your latest Cursor session. Beacon retrieves the relevant context in milliseconds so your next agent can pick up where the last one left off. 4. Your agents learn from your past work. This is where things get interesting. Beacon identifies repeated workflows and turns them into reusable skills. In our demo, it discovered a recurring UI development workflow and generated a skill containing the exact dev server commands, screenshot steps, and deployment instructions. You teach one agent something once. Every other agent can benefit. 5. Stop accumulating skills nobody uses. Have 100 skills but only use five? Beacon analyzes actual usage across thousands of sessions and identifies skills worth keeping, combining, or removing. Your agent's memory gets more useful, not just bigger. 6. Security rules that follow you across every harness. Beacon includes hundreds of detection rules that work across agents. It can identify risky behavior, including sequences where an agent reads sensitive credentials and then makes an outbound network request. 7. It even caught a real credential leak. While reviewing Justin's actual Cursor history, Beacon surfaced an incident where part of a production database password had been sent to a model provider. That's the power of having visibility into what your agents are actually doing. 8. One prompt to get started. Completely open source. Paste a setup prompt into your coding agent and you're off. Keep everything local on your machine, or use Beacon Cloud for free. If you're juggling multiple coding agents, you need to check this out. Drop a like and share it with someone facing the same issue. Beacon on GitHub: (don't forget to star 🌟) Enjoy the episode. Cheers!
29:01

I gave Claude Code, Codex, and Cursor a self-improving, shared MEMORY. Now my coding agents learn from each other, and their knowledge follows me wherever I work. Coding agents work in silos. Your corrections in Cursor don't carry over to Claude Code, and skills built in Codex don't automatically transfer to other harnesses. So switching tools often means starting from scratch. What if every coding agent could learn from everything you've already done? I invited Justin D'Souza, co-founder of Asymptote Labs, to show me how to make this possible with Beacon, a 100% open-source memory layer for coding agents. We set it up live, explored real coding sessions, and watched Beacon turn past work into reusable knowledge. Here's what I learned: 1. One memory layer for 20+ coding agents. Beacon captures activity across Claude Code, Cursor, Codex, and 20+ harnesses using OpenTelemetry, hooks, and local session files. Everything gets normalized into a single format, regardless of which agent you're using. 2. Your entire coding history becomes searchable. Every prompt, tool call, command, file change, and response is captured in a structured trace. Instead of losing valuable context when a session ends, you build a searchable history of everything your agents have done. 3. Switch agents without starting over. Hit your usage limit in Cursor? Open Claude Code and ask it to continue your latest Cursor session. Beacon retrieves the relevant context in milliseconds so your next agent can pick up where the last one left off. 4. Your agents learn from your past work. This is where things get interesting. Beacon identifies repeated workflows and turns them into reusable skills. In our demo, it discovered a recurring UI development workflow and generated a skill containing the exact dev server commands, screenshot steps, and deployment instructions. You teach one agent something once. Every other agent can benefit. 5. Stop accumulating skills nobody uses. Have 100 skills but only use five? Beacon analyzes actual usage across thousands of sessions and identifies skills worth keeping, combining, or removing. Your agent's memory gets more useful, not just bigger. 6. Security rules that follow you across every harness. Beacon includes hundreds of detection rules that work across agents. It can identify risky behavior, including sequences where an agent reads sensitive credentials and then makes an outbound network request. 7. It even caught a real credential leak. While reviewing Justin's actual Cursor history, Beacon surfaced an incident where part of a production database password had been sent to a model provider. That's the power of having visibility into what your agents are actually doing. 8. One prompt to get started. Completely open source. Paste a setup prompt into your coding agent and you're off. Keep everything local on your machine, or use Beacon Cloud for free. If you're juggling multiple coding agents, you need to check this out. Drop a like and share it with someone facing the same issue. Beacon on GitHub: (don't forget to star 🌟) Enjoy the episode. Cheers!

Akshay 🚀

12,996 просмотров • 11 часов назад

I BUILT MY OWN OFFICE AND GROK BOT IS THE BOSS Just look at what my workplace/office looks like. Before, AI just waited for me to open a chat and type a prompt. Now I run a real digital office: persistent agents with clear roles, a shared cloud computer, browser, and terminal. They keep working 24/7 even when my laptop is closed. And the best part - it’s easy. Download the app → sign in → create the “Chief” → give them job titles (just like briefing new hires) → show a task once → connect Telegram. > No experience needed. > No VPS. > No coding. > Everything is straightforward. I just drop a goal in Telegram and the bots break it down, delegate, and deliver. I only make the decisions. Grok Bot isn’t a chatbot. It’s a team you can actually build in one evening - even if you’ve never created agents before.
0:26

I BUILT MY OWN OFFICE AND GROK BOT IS THE BOSS Just look at what my workplace/office looks like. Before, AI just waited for me to open a chat and type a prompt. Now I run a real digital office: persistent agents with clear roles, a shared cloud computer, browser, and terminal. They keep working 24/7 even when my laptop is closed. And the best part - it’s easy. Download the app → sign in → create the “Chief” → give them job titles (just like briefing new hires) → show a task once → connect Telegram. > No experience needed. > No VPS. > No coding. > Everything is straightforward. I just drop a goal in Telegram and the bots break it down, delegate, and deliver. I only make the decisions. Grok Bot isn’t a chatbot. It’s a team you can actually build in one evening - even if you’ve never created agents before.

Aleiah

983,378 просмотров • 1 месяц назад

I built something I believe is useful for agentic coding today. I’ve been too worried it’s not the best it can be, but my wife encouraged me to fail fast if I was worried about failure, so here we are. Introducing Kontinuo by Pull Base, the continuity layer for your AI coding agents. You’re mid-task, you hit a rate limit on Claude, and you want to keep going on Codex or Cursor. But the next agent has no idea what just happened. Kontinuo fixes that, it leaves a verifiable context log the next agent can actually use and it’s really token efficient. Check it out: Use it, break it. I hope it’s useful to at least one person.
1:00

I built something I believe is useful for agentic coding today. I’ve been too worried it’s not the best it can be, but my wife encouraged me to fail fast if I was worried about failure, so here we are. Introducing Kontinuo by Pull Base, the continuity layer for your AI coding agents. You’re mid-task, you hit a rate limit on Claude, and you want to keep going on Codex or Cursor. But the next agent has no idea what just happened. Kontinuo fixes that, it leaves a verifiable context log the next agent can actually use and it’s really token efficient. Check it out: Use it, break it. I hope it’s useful to at least one person.

Big Sheddy 🦅

61,941 просмотров • 3 месяцев назад

Running operations used to take me 10+ hours/week. Now it takes 30 minutes. Here’s what changed: → I stopped using AI as a chatbot → I started using Perplexity Computer as a system In one workflow, it: • Reads my Slack updates • Checks my calendar • Pulls data from sheets • Generates a full weekly report • Summarizes key decisions • Flags risks automatically No switching tools. No manual work. This is the shift most people are missing: AI isn’t for asking questions anymore. It’s for executing workflows. If you’re still “chatting” with AI… you’re already behind. see what you’ve been missing—start now, explore key features in minutes, and feel the difference . Try it now:
0:21

Running operations used to take me 10+ hours/week. Now it takes 30 minutes. Here’s what changed: → I stopped using AI as a chatbot → I started using Perplexity Computer as a system In one workflow, it: • Reads my Slack updates • Checks my calendar • Pulls data from sheets • Generates a full weekly report • Summarizes key decisions • Flags risks automatically No switching tools. No manual work. This is the shift most people are missing: AI isn’t for asking questions anymore. It’s for executing workflows. If you’re still “chatting” with AI… you’re already behind. see what you’ve been missing—start now, explore key features in minutes, and feel the difference . Try it now:

Aryan Rakib

39,084 просмотров • 6 месяцев назад