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.

Debugging localhost webhooks shouldn’t be a guessing game. Hookdeck CLI v1.1.0 adds: - Session Filters – isolate event types - Interactive Mode – inspect & replay from your terminal Full demo below ↓

Hookdeck

1,375 subscribers

2,448,010 views • 10 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

15 Comments

Shahidullah Muffakir10 months ago

This is so cool and useful. I really needed this today for debugging Twilio's webhooks locally.

Abhishek Gawade10 months ago

I will try this

Suresh9 months ago

Webhook debugging made simple. Session filters and interactive mode solve real developer pain points.

Nikhil9 months ago

Session filters + replay mode is genuinely useful for webhook debugging. Most devs I know waste hours fumbling through logs trying to match the exact payload that broke production. Being able to isolate and replay specific events from terminal changes that game completely. Solid execution here.

Susie9 months ago

这个更新挺实用的——终端里直接过滤事件和回放能省不少排查时间。请问 replay 时能否保留原始签名/headers 用于重现签名校验失败的场景？

Aman Ali10 months ago

A useful tool

Crypto Astra10 months ago

Love these updates — makes local debugging so much smoother. 🔥

ibomoko10 months ago

Ngrok is a good way of achieving this.

Hookdeck10 months ago

Unfortunately not. Ngrok can only support 1 user per tunnel, which is a major limitation for webhooks. The Hookdeck CLI supports an unlimited number of developers connecting to the same URL simultaneously. Ngrok is great for bidirectional (synchronous) use cases; it falls short for teams working with webhooks.

Ari Bambang9 months ago

I love this tool

K K K K I I I I10 months ago

clean upgrade

luis miguel10 months ago

本地钩子调试不再盲猜，Session Filters 超实用，Interactive Mode 超顺滑！

Olivia9 months ago

本地调试能这么丝滑才是爽事啊

Pablo Martinez9 months ago

@grok explicame para que me sirve esta herramienta y dame ejemplos

Johnson Adedokun10 months ago

Great🔥

Related Videos

The Hookdeck CLI is a free - no account required - alternative to ngrok for asynchronous web development. ✅ Permanent URLs ✅ Inspect and replay requests ✅ Works on Mac, Linux, and Windows

The Hookdeck CLI is a free - no account required - alternative to ngrok for asynchronous web development. ✅ Permanent URLs ✅ Inspect and replay requests ✅ Works on Mac, Linux, and Windows

Hookdeck

240,249 views • 2 years ago

I am happy to announce Hookdrop This is for every developer and team who's ever debugged a Stripe or Paystack webhook by squinting at logs and praying. Debugging webhooks shouldn't mean babysitting a provider dashboard. hookdrop gives you a permanent URL, so every webhook that hits it shows up instantly, live. Click it, see the full payload data, and verify their signature is actually real (most tools don't even do this part). Then replay it straight to your localhost. No need to trigger from the provider again every time you fix a bug. Get started at: [

I am happy to announce Hookdrop This is for every developer and team who's ever debugged a Stripe or Paystack webhook by squinting at logs and praying. Debugging webhooks shouldn't mean babysitting a provider dashboard. hookdrop gives you a permanent URL, so every webhook that hits it shows up instantly, live. Click it, see the full payload data, and verify their signature is actually real (most tools don't even do this part). Then replay it straight to your localhost. No need to trigger from the provider again every time you fix a bug. Get started at: [

Cap-EO 👨🏾‍💻

26,530 views • 2 months ago

WeRobot: The BIGGEST $TSLA Event Since Model 3! 🚀 Insights from Cern Basher! • Tesla announces a big event on 10/10 called “WeRobot,” which Elon Musk says will be historic. • The event might show off different types of robots and robot taxis, not just Optimus. • Elon Musk hints that the event could mark a major tech shift, like the launch of the iPhone. • People are guessing that different robot designs, including bigger and smaller vehicles, could be showcased. • Tesla is focusing more on utility and safety for its Robotaxi vehicles instead of exterior design. • Tesla’s unbox method lets them build vehicle sides separately and assemble them, allowing for different designs without needing separate front and back parts. • The Robotaxi event might include live demos, participant rides, and a full app demo showing everything from ordering to completing a ride. • There’s speculation that the Robotaxi Network could start with supervised rides under a name like “Drive” before moving to fully autonomous rides. Tesla Elon Musk

WeRobot: The BIGGEST $TSLA Event Since Model 3! 🚀 Insights from Cern Basher! • Tesla announces a big event on 10/10 called “WeRobot,” which Elon Musk says will be historic. • The event might show off different types of robots and robot taxis, not just Optimus. • Elon Musk hints that the event could mark a major tech shift, like the launch of the iPhone. • People are guessing that different robot designs, including bigger and smaller vehicles, could be showcased. • Tesla is focusing more on utility and safety for its Robotaxi vehicles instead of exterior design. • Tesla’s unbox method lets them build vehicle sides separately and assemble them, allowing for different designs without needing separate front and back parts. • The Robotaxi event might include live demos, participant rides, and a full app demo showing everything from ordering to completing a ride. • There’s speculation that the Robotaxi Network could start with supervised rides under a name like “Drive” before moving to fully autonomous rides. Tesla Elon Musk

Herbert Ong

33,991 views • 2 years ago

🚨 $KATA FAM – THE STEAM DEMO GOES LIVE TOMORROW! 🔥 💰WIN $250 in $KATA Giveaway below! Tomorrow is the day. The Katana Inu Steam Demo will be live from April 11 to April 21. 🔥 Steam: This is your chance to jump in, play the game, and help us make some real noise around the demo launch. 😍 Once the demo phase is over, we already have a lot planned. We will share all details with you over the coming weeks, but one thing is already clear: 🎮 As a creator, you can expect the chance to win 2x PS5 for your community🎁 - More prizes and giveaways are also coming! Right now, we need your full support! 👉Wishlist the game on Steam & Play it 👉Play the demo as soon as it goes live 👉Leave your feedback on Steam, if you enjoy the game 👉Help us push Katana Inu to a bigger audience Every wishlist, every session, and every piece of feedback helps a lot! Let’s show what this community is made of. 💥 BONUS $KATA GIVEAWAY ALERT! We’re adding EVEN MORE fuel to the fire… 👉 5x $50 in $KATA 💰 Total: $250 in $KATA up for grabs! 🖼 1 Takeru Gensis NFT 🎯 How to participate? Join our Steam Demo between April 11 – April 21 🔥 1. Take a screenshot as proof that you play it 2. Wishlisted on Steam 3. Drop it in the comments below 👇 4. RT/QT this + Like ❤️ 5. Tag 3 person Influencer/Friend! ⚡ That’s it – you’re in! 🔥 More action = more hype 🔥 We choose random winners! Let’s make this event great and show everyone what $KATA FAM is made of 💥

🚨 $KATA FAM – THE STEAM DEMO GOES LIVE TOMORROW! 🔥 💰WIN $250 in $KATA Giveaway below! Tomorrow is the day. The Katana Inu Steam Demo will be live from April 11 to April 21. 🔥 Steam: This is your chance to jump in, play the game, and help us make some real noise around the demo launch. 😍 Once the demo phase is over, we already have a lot planned. We will share all details with you over the coming weeks, but one thing is already clear: 🎮 As a creator, you can expect the chance to win 2x PS5 for your community🎁 - More prizes and giveaways are also coming! Right now, we need your full support! 👉Wishlist the game on Steam & Play it 👉Play the demo as soon as it goes live 👉Leave your feedback on Steam, if you enjoy the game 👉Help us push Katana Inu to a bigger audience Every wishlist, every session, and every piece of feedback helps a lot! Let’s show what this community is made of. 💥 BONUS $KATA GIVEAWAY ALERT! We’re adding EVEN MORE fuel to the fire… 👉 5x $50 in $KATA 💰 Total: $250 in $KATA up for grabs! 🖼 1 Takeru Gensis NFT 🎯 How to participate? Join our Steam Demo between April 11 – April 21 🔥 1. Take a screenshot as proof that you play it 2. Wishlisted on Steam 3. Drop it in the comments below 👇 4. RT/QT this + Like ❤️ 5. Tag 3 person Influencer/Friend! ⚡ That’s it – you’re in! 🔥 More action = more hype 🔥 We choose random winners! Let’s make this event great and show everyone what $KATA FAM is made of 💥

Katana Inu Game

25,363 views • 5 months ago

Exclusive update 🚨: Dear #Microsoft Xbox Division Team Leaders, Executives, and Decision Makers, A golden opportunity you shouldn’t miss! GameStudio In-D (📧 gamestudio.inD@gmail.com)—are eager to collaborate with #Xbox, and for them, it’s a dream come true! #Project Gray is a breathtaking open-world sci-fi action RPG, built in Unreal Engine 5 and in development for over six years. The 2022 demo stunned players—imagine what it could become with #Xbox’s support! 📽️ Check out the gameplay clip below! 🔹 Actual in-game footage from a two-year-old demo. 🔹 With Xbox’s backing, this could be a AAA next-gen masterpiece. 💡 XBOX, let’s make this happen! Xbox community—what do you think? Drop your thoughts, share this post, and let’s make some noise! 🔥

Exclusive update 🚨: Dear #Microsoft Xbox Division Team Leaders, Executives, and Decision Makers, A golden opportunity you shouldn’t miss! GameStudio In-D (📧 [email protected])—are eager to collaborate with #Xbox, and for them, it’s a dream come true! #Project Gray is a breathtaking open-world sci-fi action RPG, built in Unreal Engine 5 and in development for over six years. The 2022 demo stunned players—imagine what it could become with #Xbox’s support! 📽️ Check out the gameplay clip below! 🔹 Actual in-game footage from a two-year-old demo. 🔹 With Xbox’s backing, this could be a AAA next-gen masterpiece. 💡 XBOX, let’s make this happen! Xbox community—what do you think? Drop your thoughts, share this post, and let’s make some noise! 🔥

WolfOfDarkness®

35,577 views • 1 year ago

10 GitHub repos with ⭐ 450k+ combined stars that stop your agent from wasting tokens 1. caveman 98k⭐ - makes your AI agent talk like a caveman. Same answers, 65% fewer output tokens. 2. rtk 76k⭐ - CLI proxy that filters git/test/docker output before it hits your context. Up to 90% less bash noise. 3. mem0 63k⭐ - memory layer for AI agents. Stops your agent from re-explaining the same context every session. 4. context7 60.7k⭐ - pulls exact, up-to-date docs into context instead of your agent guessing and burning tokens on retries. 5. aider 48k⭐ - builds a map of your repo instead of loading the whole codebase into context. 6. code-review-graph 30k⭐ - graphs your codebase so your agent reads 2-3 files instead of the whole repo. Up to 376x fewer tokens per question. 7. serena 28k⭐ - gives agents symbol-level code access instead of reading full files line by line. 8. repomix 28k⭐ - compresses your entire repo into an AI-friendly format. ~70% token reduction. 9. ccusage 18k⭐ - shows you exactly where your Claude Code sessions are burning tokens. 10. GPTCache 8k⭐ - semantic cache for LLM calls. Stop paying twice for the same question. Save this before your next agent session burns through your subscription 👇

10 GitHub repos with ⭐ 450k+ combined stars that stop your agent from wasting tokens 1. caveman 98k⭐ - makes your AI agent talk like a caveman. Same answers, 65% fewer output tokens. 2. rtk 76k⭐ - CLI proxy that filters git/test/docker output before it hits your context. Up to 90% less bash noise. 3. mem0 63k⭐ - memory layer for AI agents. Stops your agent from re-explaining the same context every session. 4. context7 60.7k⭐ - pulls exact, up-to-date docs into context instead of your agent guessing and burning tokens on retries. 5. aider 48k⭐ - builds a map of your repo instead of loading the whole codebase into context. 6. code-review-graph 30k⭐ - graphs your codebase so your agent reads 2-3 files instead of the whole repo. Up to 376x fewer tokens per question. 7. serena 28k⭐ - gives agents symbol-level code access instead of reading full files line by line. 8. repomix 28k⭐ - compresses your entire repo into an AI-friendly format. ~70% token reduction. 9. ccusage 18k⭐ - shows you exactly where your Claude Code sessions are burning tokens. 10. GPTCache 8k⭐ - semantic cache for LLM calls. Stop paying twice for the same question. Save this before your next agent session burns through your subscription 👇

unicode

68,057 views • 1 month ago

$REPLAY FILES BROKEN (FIXED + STEP BY STEP GUIDE) Hey! Currently there's a bug with replay files that prevents replays from before the latest Rocket League patch to load/work. As a creator, this severely impacts my workflow, and waiting for a patch could take a while. So to make sure I, and everyone else out there can continue to work, I've tried to find a solution. Initially I messed around with installing older Rocket League versions through the steam console, and trying to get the Injector from Bakkesmod to downgrade to the matching Rocket League version, however this proved to be tedious and honestly fruitless. So instead I turned to the modding community where I was quickly directed towards Martin, who ended up fixing the replay issue and building a handy tool. WHAT YOU'LL NEED: RocketRP: Microsoft. NET 9.0 Runtime: HOW TO: Step 1: Download (if your antivirus flags it, allow list it. Running unknown files is ALWAYS at your own risk, however I run the setup as well and the sourcecode is available to check for when you're in doubt). Step 2: Download the .NET 9.0 console framework for windows, or your respective platform. Step 3: Install the .NET 9.0 console framework through the downloaded .exe Step 4: Unzip/Extract the "RocketRP .cli .zip" file Step 5: Right click the extracted folder and select "Open in Terminal". If that option doesn't appear you need to click more options, and / or open with, and manually select Powershell or your preferred terminal of choice. Step 6: leave the terminal window open and go to: %USERPROFILE%\Documents\My Games\Rocket League\TAGame\Demos Step 7: Select the replays you want and place these in a new folder somewhere easily accessible. Make sure to back them up just in case* Step 8: Right click the replay you want to fix, and then select "copy as path" Step 9: In notepad or similar, copy this command: .\RocketRP.CLI.exe -r " " -m Repack --backup --legacy-fix true Make sure to replace the " " with the link you copied from the replay in step 8. For a breakdown of the command, check the video or use the help command in the terminal. Step 10: In the terminal, paste the command we created in step 9, then press enter. This should create a backup file of your replay, and it should create a new replay file that has the patch applied. NOTE: Right now, doing full folders isn't working, therefore you'll have to do this 1 replay at a time, untill I post a fix in the comments. Step 11: Put the newly generated replay in the demos folder (step 6) and load back into Rocket League. Your replay should now work as intended! Please note if you get any errors, you mostlikely didn't install the .NET 9.0 console correctly, or you have to check your command for typos. Huge thanks to Martin for helping me out with this, here's his paypal if you want to show him some appreciation: And if you're feeling EXTRA generous, here's my youtube. Consider subscribing if this helped you out!: If you have any questions, leave them below and I'll try to answer them the best I can!$

REPLAY FILES BROKEN (FIXED + STEP BY STEP GUIDE) Hey! Currently there's a bug with replay files that prevents replays from before the latest Rocket League patch to load/work. As a creator, this severely impacts my workflow, and waiting for a patch could take a while. So to make sure I, and everyone else out there can continue to work, I've tried to find a solution. Initially I messed around with installing older Rocket League versions through the steam console, and trying to get the Injector from Bakkesmod to downgrade to the matching Rocket League version, however this proved to be tedious and honestly fruitless. So instead I turned to the modding community where I was quickly directed towards Martin, who ended up fixing the replay issue and building a handy tool. WHAT YOU'LL NEED: RocketRP: Microsoft. NET 9.0 Runtime: HOW TO: Step 1: Download (if your antivirus flags it, allow list it. Running unknown files is ALWAYS at your own risk, however I run the setup as well and the sourcecode is available to check for when you're in doubt). Step 2: Download the .NET 9.0 console framework for windows, or your respective platform. Step 3: Install the .NET 9.0 console framework through the downloaded .exe Step 4: Unzip/Extract the "RocketRP .cli .zip" file Step 5: Right click the extracted folder and select "Open in Terminal". If that option doesn't appear you need to click more options, and / or open with, and manually select Powershell or your preferred terminal of choice. Step 6: leave the terminal window open and go to: %USERPROFILE%\Documents\My Games\Rocket League\TAGame\Demos Step 7: Select the replays you want and place these in a new folder somewhere easily accessible. Make sure to back them up just in case* Step 8: Right click the replay you want to fix, and then select "copy as path" Step 9: In notepad or similar, copy this command: .\RocketRP.CLI.exe -r " " -m Repack --backup --legacy-fix true Make sure to replace the " " with the link you copied from the replay in step 8. For a breakdown of the command, check the video or use the help command in the terminal. Step 10: In the terminal, paste the command we created in step 9, then press enter. This should create a backup file of your replay, and it should create a new replay file that has the patch applied. NOTE: Right now, doing full folders isn't working, therefore you'll have to do this 1 replay at a time, untill I post a fix in the comments. Step 11: Put the newly generated replay in the demos folder (step 6) and load back into Rocket League. Your replay should now work as intended! Please note if you get any errors, you mostlikely didn't install the .NET 9.0 console correctly, or you have to check your command for typos. Huge thanks to Martin for helping me out with this, here's his paypal if you want to show him some appreciation: And if you're feeling EXTRA generous, here's my youtube. Consider subscribing if this helped you out!: If you have any questions, leave them below and I'll try to answer them the best I can!

GGM1 Yota

14,018 views • 1 year ago

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,540 views • 4 months ago

Grok Build CLI just got an update with v1.0.5! 🚀 Changelog v1.0.5 Features: • GROK_CONFIG and GROK_CONFIG_PATH environment variables now let launchers override selected config settings without editing config.toml. • Worktrees under ~/.grok/worktrees are now automatically reclaimed when safe, with strong safeguards that never delete a user's last copy. • Hook policy blocks now correctly report "Turn blocked by a hook" instead of "Turn cancelled by user." • Image and video generation now limits how many calls the model can request in one step to avoid overload. • Arabic and Persian text can now be reordered correctly in the terminal UI. Turn on in /settings. • Reasoning effort can now be supplied when an ACP client opens or resumes a session. • Session titles now refresh early in the conversation and stay stable; /resume shows a recap and last-turn summary when available. • GROK_FORCE_LOGIN_TEAM_ID environment variable now lets launchers restrict interactive login to one or more teams. • Preparing spinner now shows readable labels such as "Writing file…" and "Writing edit…" for common tools. Bug Fixes: • Tool calls (shell, grep, list_dir) no longer fail for the rest of a session if /dev/null is removed. • Agent skill discovery now resolves the user's home directory correctly on Windows. • MCP tool calls now show clearer spinner text instead of the raw wire name while arguments are still arriving. • grok inspect no longer crashes when its output is piped into a command that closes the pipe early. • Minimal mode no longer truncates a still-streaming assistant reply when thinking blocks are interleaved.

Grok Build CLI just got an update with v1.0.5! 🚀 Changelog v1.0.5 Features: • GROK_CONFIG and GROK_CONFIG_PATH environment variables now let launchers override selected config settings without editing config.toml. • Worktrees under ~/.grok/worktrees are now automatically reclaimed when safe, with strong safeguards that never delete a user's last copy. • Hook policy blocks now correctly report "Turn blocked by a hook" instead of "Turn cancelled by user." • Image and video generation now limits how many calls the model can request in one step to avoid overload. • Arabic and Persian text can now be reordered correctly in the terminal UI. Turn on in /settings. • Reasoning effort can now be supplied when an ACP client opens or resumes a session. • Session titles now refresh early in the conversation and stay stable; /resume shows a recap and last-turn summary when available. • GROK_FORCE_LOGIN_TEAM_ID environment variable now lets launchers restrict interactive login to one or more teams. • Preparing spinner now shows readable labels such as "Writing file…" and "Writing edit…" for common tools. Bug Fixes: • Tool calls (shell, grep, list_dir) no longer fail for the rest of a session if /dev/null is removed. • Agent skill discovery now resolves the user's home directory correctly on Windows. • MCP tool calls now show clearer spinner text instead of the raw wire name while arguments are still arriving. • grok inspect no longer crashes when its output is piped into a command that closes the pipe early. • Minimal mode no longer truncates a still-streaming assistant reply when thinking blocks are interleaved.

Puck

31,441 views • 1 month ago

Introducing GGEZ: The Nextjs for ThreeJS Games It's an open source framework which adds all the missing pieces to vibe code better ThreeJS games It has full codex integration, so a $20 ChatGPT sub is enough to build games! Literally "bun run start" and you have the full development environment on localhost 0. GGEZ Runtime - Abstraction layer over physics libraries - Character Controllers - It's just ThreeJS, no magic - Load ggez scenes and animations automatically 1. Trident - a World Editor - Codex World agent - A full editor to build scenes - Including Mesh editing, vertex, edge, face - Terrain sculpting - Physics and Player Controller settings - It's just exporting json files and glb assets, no magic 2. Animation Studio - The best you can find on the web - Codex Animation agent - Build state machines and animation graphs - Multi dimensional blend trees - Clip Editor: Create new animations with codex or edit keyframes - Equipment Editor: Never miss the placement of your rifle anymore - ROOT MOTION SUPPORT 3. GGEZ CLI Yea relax, it works fully headless and you can just create new games with bunx create-ggez new-game But at this point just use vanilla threejs?? Anyways if you are like me and you can't guess with code where objects should be placed and you are fifty prompts deep into figuring out where that box should be placed, this is for you If you are an anti AI game developer who insists that this is slop, then just leave a raging comment below please it's good for the algo 🙏 The whole thing is absolutely experimental and things will break as i move very fast, but I will be building my game with it so i will make sure it becomes stable asap! Link to repo below

Introducing GGEZ: The Nextjs for ThreeJS Games It's an open source framework which adds all the missing pieces to vibe code better ThreeJS games It has full codex integration, so a $20 ChatGPT sub is enough to build games! Literally "bun run start" and you have the full development environment on localhost 0. GGEZ Runtime - Abstraction layer over physics libraries - Character Controllers - It's just ThreeJS, no magic - Load ggez scenes and animations automatically 1. Trident - a World Editor - Codex World agent - A full editor to build scenes - Including Mesh editing, vertex, edge, face - Terrain sculpting - Physics and Player Controller settings - It's just exporting json files and glb assets, no magic 2. Animation Studio - The best you can find on the web - Codex Animation agent - Build state machines and animation graphs - Multi dimensional blend trees - Clip Editor: Create new animations with codex or edit keyframes - Equipment Editor: Never miss the placement of your rifle anymore - ROOT MOTION SUPPORT 3. GGEZ CLI Yea relax, it works fully headless and you can just create new games with bunx create-ggez new-game But at this point just use vanilla threejs?? Anyways if you are like me and you can't guess with code where objects should be placed and you are fifty prompts deep into figuring out where that box should be placed, this is for you If you are an anti AI game developer who insists that this is slop, then just leave a raging comment below please it's good for the algo 🙏 The whole thing is absolutely experimental and things will break as i move very fast, but I will be building my game with it so i will make sure it becomes stable asap! Link to repo below

robot

44,009 views • 6 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

For developers, Gemini 3 Pro offers unparalleled results across every major AI benchmark compared to Gemini 2.5 Pro. Here three ways Gemini 3 Pro can improve your workflow today: 1. Gemini 3 Pro fits right into existing production agent and coding workflows. It is also integrated into development environment experiences across the ecosystem of developer products like Google AI Studio, Gemini CLI, and Android Studio. 2. We introduced Google Google Antigravity, a new agentic development platform that reimagines how the model and IDE work together. It enables developers to manage agents to work at a higher, task-oriented level collaborating with agents while they build. 3. We’ve built Google AI Studio to be your fastest path from a prompt to an AI-native app. Build mode lets you add AI capabilities faster than ever, automatically wiring up the right models and APIs, while features like annotations enable fast and intuitive iteration. Whether you’re building a one-shot prompt game or an interactive landing page from unstructured voice notes, you can bring any idea to life with Gemini 3.

For developers, Gemini 3 Pro offers unparalleled results across every major AI benchmark compared to Gemini 2.5 Pro. Here three ways Gemini 3 Pro can improve your workflow today: 1. Gemini 3 Pro fits right into existing production agent and coding workflows. It is also integrated into development environment experiences across the ecosystem of developer products like Google AI Studio, Gemini CLI, and Android Studio. 2. We introduced Google Google Antigravity, a new agentic development platform that reimagines how the model and IDE work together. It enables developers to manage agents to work at a higher, task-oriented level collaborating with agents while they build. 3. We’ve built Google AI Studio to be your fastest path from a prompt to an AI-native app. Build mode lets you add AI capabilities faster than ever, automatically wiring up the right models and APIs, while features like annotations enable fast and intuitive iteration. Whether you’re building a one-shot prompt game or an interactive landing page from unstructured voice notes, you can bring any idea to life with Gemini 3.

Google AI

136,648 views • 10 months ago

We just shipped a completely new concept for web interaction. Live on three․ws, we are thrilled to showcase this demo of persistent, interactive 3D AI Agents that live right in your browser. As the first mover in this space, we are achieving what hasn't been done before: seamlessly bridging the gap between traditional flat web pages and fully immersive, spatial 3D environments. We are fundamentally shifting how humans experience the internet. Here's how. Intelligent AI Agents. Your 3D companion drops right into the screen, tracks your cursor, and interacts with you based on the exact page you are viewing. Context-Aware Guide. Knows exactly where visitors are. It can point out and encourage clicks on the most important parts of a site. Highly Interactive. Turns to follow your cursor in real-time, waves when you navigate, and idles naturally. Playground Mode. Click your avatar and it seamlessly detaches into a full-page 3D stroll or platformer right in the browser. Use keyboard arrows on desktop and joystick on mobile. Choose Your Avatar. Pick exactly who walks the web with you from a fully customizable, hot-swappable roster. Polite & Lightweight. Built with smart compression and shared animation files. It monitors browser memory to guarantee zero slowdowns and respects "reduced motion" accessibility settings. Flat websites will be gone before you know it. The future is interactive, the future is intelligent. It's time to break AI out the chatbox. three․ws

three.ws

22,815 views • 3 months ago

Meet Hermes3D A live 3D command center for Hermes Agents Some of you might remember Claw3D It went viral, but it was built around OpenClaw. After moving all my workflows to Hermes, continuing to build it no longer made sense So I rebuilt the entire idea for Hermes Hermes Bot Mode already gives every agent its own role, model, memory, skills, tools, and personality. Hermes3D gives that team an office See which agents are working See who is blocked Inspect their tasks Open the Kanban board Walk up and talk to them And when agents communicate, delegate work, or hand tasks to each other, you will be able to watch it happen inside the office in real time Your AI team should not feel like ten invisible processes hiding inside terminal tabs. It should feel like a workplace you can actually see and control. Claw3D was the prototype Hermes3D is the real vision And of course, it is Open Source Demo below. Repo link in the first comment

Meet Hermes3D A live 3D command center for Hermes Agents Some of you might remember Claw3D It went viral, but it was built around OpenClaw. After moving all my workflows to Hermes, continuing to build it no longer made sense So I rebuilt the entire idea for Hermes Hermes Bot Mode already gives every agent its own role, model, memory, skills, tools, and personality. Hermes3D gives that team an office See which agents are working See who is blocked Inspect their tasks Open the Kanban board Walk up and talk to them And when agents communicate, delegate work, or hand tasks to each other, you will be able to watch it happen inside the office in real time Your AI team should not feel like ten invisible processes hiding inside terminal tabs. It should feel like a workplace you can actually see and control. Claw3D was the prototype Hermes3D is the real vision And of course, it is Open Source Demo below. Repo link in the first comment

Luke The Dev

57,527 views • 1 month ago

Grok Build CLI just got an update with v0.2.113! 🚀 Changelog v0.2.113 Features: • MCP servers can now be enabled or disabled directly from the CLI with `grok mcp enable ` and `grok mcp disable `. • Full plan markdown can now be copied to the clipboard with `y` during plan approval or preview. • Added support for the new SuperGrok Plus subscription tier in authentication and feature gating. • Enabled automatic recovery from repetitive loops in model output by default. Performance: • Cold start shows the UI instantly while models and settings load in the background. • Large session forks and resumes now use far less memory and avoid spikes. • Prevented thread exhaustion on high-core shared machines by limiting the workspace daemon's worker threads. Bug Fixes: • Terminal command output is no longer lost or duplicated when the gateway is unreachable. • Invalid MCP server entries in config.toml no longer prevent Grok from starting; problems are shown in `grok inspect`. • SessionEnd hooks now run on exit in non-leader TUI and headless sessions. • Paste chips now display with the correct background in inline prompts and question inputs. • Pasted content chips now behave consistently when editing answers in the question view. • Background task status now shows only elapsed duration instead of absolute timestamps. • Session lists no longer drop real sessions when the remote registry reports an outdated turn count of zero. • /loop now stores prompts that include stop conditions so recurring tasks can terminate themselves when done. • Reduced spurious warning messages for common auth and config scenarios. • Fixed conda activation (and other sourced scripts that read $@) when using persistent or login-capture shells. • Fixed stuck background-task tray rows after long foreground shell commands complete. • Agent subprocesses and idle inhibitors are now cleaned up when the parent CLI process dies unexpectedly. • Fixed truncated plans in minimal mode and improved visual separation between reasoning and output (including NO_COLOR). • Fixed credential loss across multiple grok processes sharing the same auth file. • Fixed doubled Enter and other keys on older Alacritty terminals. • Fixed false paywall messages for free-tier and unmatched users.

Grok Build CLI just got an update with v0.2.113! 🚀 Changelog v0.2.113 Features: • MCP servers can now be enabled or disabled directly from the CLI with `grok mcp enable ` and `grok mcp disable `. • Full plan markdown can now be copied to the clipboard with `y` during plan approval or preview. • Added support for the new SuperGrok Plus subscription tier in authentication and feature gating. • Enabled automatic recovery from repetitive loops in model output by default. Performance: • Cold start shows the UI instantly while models and settings load in the background. • Large session forks and resumes now use far less memory and avoid spikes. • Prevented thread exhaustion on high-core shared machines by limiting the workspace daemon's worker threads. Bug Fixes: • Terminal command output is no longer lost or duplicated when the gateway is unreachable. • Invalid MCP server entries in config.toml no longer prevent Grok from starting; problems are shown in `grok inspect`. • SessionEnd hooks now run on exit in non-leader TUI and headless sessions. • Paste chips now display with the correct background in inline prompts and question inputs. • Pasted content chips now behave consistently when editing answers in the question view. • Background task status now shows only elapsed duration instead of absolute timestamps. • Session lists no longer drop real sessions when the remote registry reports an outdated turn count of zero. • /loop now stores prompts that include stop conditions so recurring tasks can terminate themselves when done. • Reduced spurious warning messages for common auth and config scenarios. • Fixed conda activation (and other sourced scripts that read $@) when using persistent or login-capture shells. • Fixed stuck background-task tray rows after long foreground shell commands complete. • Agent subprocesses and idle inhibitors are now cleaned up when the parent CLI process dies unexpectedly. • Fixed truncated plans in minimal mode and improved visual separation between reasoning and output (including NO_COLOR). • Fixed credential loss across multiple grok processes sharing the same auth file. • Fixed doubled Enter and other keys on older Alacritty terminals. • Fixed false paywall messages for free-tier and unmatched users.

Puck

94,737 views • 2 months ago

"Together, we step into this ever-after moment." Trailer of New 5-Star Interactive Memory Series [Witnessed By Deepspace] Released! 💫Follow Love and Deepspace and Repost for a chance to win $50 (5 winners)! 💍Event Duration: From 05:00 on Jul. 3 to 04:59 on Jul. 22 (Server Time) You can select three out of the five event-limited 5-Star Memories: [Xavier: Starfall Sanctuary], [Zayne: Iceborn Warmth], [Rafayel: Destined Dawntide], [Sylus: Alternative Darkborne], and [Caleb: Wayward Wonderland]. The drop rate of the 3 Memories you selected will be significantly increased. Each time you obtain a 5-Star Memory, there's a 75% chance it will be one of the three Memories you selected. *Tips: 1. During the event, you can change your selected Memories at any time. If you obtain a 5-Star Memory in a wish, there's a 25% chance that it will be an unselected Memory or a permanent 5-Star Memory. 2. After the event ends, the five event-limited Memories will not be obtainable through other means and will not enter the permanent Wish Pool: Xspace Echo. 3. The Wish event features Precise Wish and a pity system. For more details, please check the in-game rule page. 💍First Top-Up Bonus & First Top-Up Memory Gift Reset From 05:00 on Jul. 3 (server time), the [First Top-Up Gift] for all Crystal packages in Shop will reset. The First Top-Up Memory Gift event on the main screen will be updated with [Sylus: Melodic Weave] and [Caleb: Summer's Echo], and reward collection progress will also be reset. From 05:00 on Jul. 3, your first purchase of any cash-paid item will allow you to select one out of the five 4-Star Memories. 💍Cumulative Wish Rewards During the event, after making a certain number of Wishes, you can claim various rewards: Universal Veil [Sunset Mist], [Deepspace Wish: Limited*20], His [Memory-Themed Outfits], and selectable [Event-Limited 5-Star Memory]. *The cumulative rewards are only available during this wish event. 💍Limited-Time Memory Growth Bonus During the event, by completing growth tasks of the event-limited 5-Star Memories, you can claim various Upgrade and Ascension Materials. When the event-limited Memories reach Rank 1, you can claim the [Special-Colored Memory-Themed Outfit] for the corresponding love interest! 💍Claim Full Formal Wear Sets: Wedding Dress, Ring & More! Obtain Memory from the [Witnessed by Deepspace] series and complete specific Memoria to claim "My" Formal Wear Set, including a wedding dress and various Accessories! Own both "My" Formal Wear Set and His Event Memory Outfit (Original or Special-colored Version) to receive "My" [Bespoke Ring] as a bonus reward! *Details on the Memories, cumulative wish rewards, and Version 4.0 events and benefits will be released starting tomorrow. Stay tuned! #LoveandDeepspace #WitnessedByDeepspace

"Together, we step into this ever-after moment." Trailer of New 5-Star Interactive Memory Series [Witnessed By Deepspace] Released! 💫Follow Love and Deepspace and Repost for a chance to win $50 (5 winners)! 💍Event Duration: From 05:00 on Jul. 3 to 04:59 on Jul. 22 (Server Time) You can select three out of the five event-limited 5-Star Memories: [Xavier: Starfall Sanctuary], [Zayne: Iceborn Warmth], [Rafayel: Destined Dawntide], [Sylus: Alternative Darkborne], and [Caleb: Wayward Wonderland]. The drop rate of the 3 Memories you selected will be significantly increased. Each time you obtain a 5-Star Memory, there's a 75% chance it will be one of the three Memories you selected. Tips: 1. During the event, you can change your selected Memories at any time. If you obtain a 5-Star Memory in a wish, there's a 25% chance that it will be an unselected Memory or a permanent 5-Star Memory. 2. After the event ends, the five event-limited Memories will not be obtainable through other means and will not enter the permanent Wish Pool: Xspace Echo. 3. The Wish event features Precise Wish and a pity system. For more details, please check the in-game rule page. 💍First Top-Up Bonus & First Top-Up Memory Gift Reset From 05:00 on Jul. 3 (server time), the [First Top-Up Gift] for all Crystal packages in Shop will reset. The First Top-Up Memory Gift event on the main screen will be updated with [Sylus: Melodic Weave] and [Caleb: Summer's Echo], and reward collection progress will also be reset. From 05:00 on Jul. 3, your first purchase of any cash-paid item will allow you to select one out of the five 4-Star Memories. 💍Cumulative Wish Rewards During the event, after making a certain number of Wishes, you can claim various rewards: Universal Veil [Sunset Mist], [Deepspace Wish: Limited20], His [Memory-Themed Outfits], and selectable [Event-Limited 5-Star Memory]. The cumulative rewards are only available during this wish event. 💍Limited-Time Memory Growth Bonus During the event, by completing growth tasks of the event-limited 5-Star Memories, you can claim various Upgrade and Ascension Materials. When the event-limited Memories reach Rank 1, you can claim the [Special-Colored Memory-Themed Outfit] for the corresponding love interest! 💍Claim Full Formal Wear Sets: Wedding Dress, Ring & More! Obtain Memory from the [Witnessed by Deepspace] series and complete specific Memoria to claim "My" Formal Wear Set, including a wedding dress and various Accessories! Own both "My" Formal Wear Set and His Event Memory Outfit (Original or Special-colored Version) to receive "My" [Bespoke Ring] as a bonus reward! Details on the Memories, cumulative wish rewards, and Version 4.0 events and benefits will be released starting tomorrow. Stay tuned! #LoveandDeepspace #WitnessedByDeepspace

Love and Deepspace

2,508,365 views • 1 year ago

The hard part about LLM failures is that their outputs rarely look like failures. The demo “works.” The output sounds coherent. The user actively uses the product. And your dashboard looks normal. Meanwhile, the system can be wrong, unsafe, or quietly driving up token spend. And you won’t notice until the damage adds up. Prompts often serve as business logic (policies, safety, and product context). But many teams ship them without the basics, such as versioning, reviewable changes, end-to-end traces, and eval gates. In production, it doesn’t crash. It degrades via wrong answers, policy misses, and surprise spending. No crash. No error. No alert. I cover this exact issue in my Stanford University CS 224G guest lecture on AI Observability and Evaluations. Here are the core ideas: • If you only log the final output, you’re guessing. Full traces show where it broke. • Evals are feedback loops. Use clear pass/fail criteria tied to outcomes. • Run evals continuously on production traces and don’t wait for support tickets. The moat isn’t prompt cleverness. It’s a measured improvement. Full lecture + blog below 👇

The hard part about LLM failures is that their outputs rarely look like failures. The demo “works.” The output sounds coherent. The user actively uses the product. And your dashboard looks normal. Meanwhile, the system can be wrong, unsafe, or quietly driving up token spend. And you won’t notice until the damage adds up. Prompts often serve as business logic (policies, safety, and product context). But many teams ship them without the basics, such as versioning, reviewable changes, end-to-end traces, and eval gates. In production, it doesn’t crash. It degrades via wrong answers, policy misses, and surprise spending. No crash. No error. No alert. I cover this exact issue in my Stanford University CS 224G guest lecture on AI Observability and Evaluations. Here are the core ideas: • If you only log the final output, you’re guessing. Full traces show where it broke. • Evals are feedback loops. Use clear pass/fail criteria tied to outcomes. • Run evals continuously on production traces and don’t wait for support tickets. The moat isn’t prompt cleverness. It’s a measured improvement. Full lecture + blog below 👇

Arsh Shah Dilbagi

20,972 views • 7 months ago