正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

box is the cheapest full VM sandbox for agents each box gets 4vCPU, 8gb ram, >50gb storage, free disk snapshots, desktop, ssh, https hosting, devtools, docker run >1000 concurrent boxes, self-serve at only $0.00001/s/box imagine all the agents you could run! try box

Anicet

4,620 subscribers

104,573 次观看 • 20 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

You can unlock Sirius for FREE by winning one match with every single brawler! 🤩 During the Sirius Release Event, you have multiple ways to unlock Sirius! 1. Win With Every Brawler Challenge Win one match with every single Brawler to unlock Sirius for free. You must own all 99 Brawlers to complete this challenge. You can also earn a Sirius Box by winning matches with 50 different Brawlers during the event. 2. Sirius Box Challenge You need 20 Sirius Boxes to complete the event and unlock Sirius. Each Sirius Box requires 2 wins.Players receive 40 tickets in total, which is exactly enough for 20 Boxes. If you earn the free Sirius Box from the 50 different Brawler wins, that means you can only lose TWICE making this the hardest challenge to complete yet! 3. Sirius Box Sirius can also be unlocked randomly from a Sirius Box during the event.This is the best Brawler Box we have ever released! It drops Brawlers (including Sirius), Coins, Power Points, XP Doublers, Credits Gadgets, Star Powers, and Hypercharges.8 Rewards per Box! #sneakpeek #brawlstars

You can unlock Sirius for FREE by winning one match with every single brawler! 🤩 During the Sirius Release Event, you have multiple ways to unlock Sirius! 1. Win With Every Brawler Challenge Win one match with every single Brawler to unlock Sirius for free. You must own all 99 Brawlers to complete this challenge. You can also earn a Sirius Box by winning matches with 50 different Brawlers during the event. 2. Sirius Box Challenge You need 20 Sirius Boxes to complete the event and unlock Sirius. Each Sirius Box requires 2 wins.Players receive 40 tickets in total, which is exactly enough for 20 Boxes. If you earn the free Sirius Box from the 50 different Brawler wins, that means you can only lose TWICE making this the hardest challenge to complete yet! 3. Sirius Box Sirius can also be unlocked randomly from a Sirius Box during the event.This is the best Brawler Box we have ever released! It drops Brawlers (including Sirius), Coins, Power Points, XP Doublers, Credits Gadgets, Star Powers, and Hypercharges.8 Rewards per Box! #sneakpeek #brawlstars

Code: AshBS

62,826 次观看 • 5 个月前

NVIDIA just made AI detect objects 10x faster by deleting one step. It's called LocateAnything, and it removes the biggest bottleneck no one else was fixing in vision-language models. Normally a model builds each bounding box one coordinate token at a time. 100 objects means thousands of tokens before an answer. NVIDIA scrapped that: their Parallel Box Decoding predicts the whole box in a single forward pass, as one atomic unit. → 12.7 boxes/sec on one H100 → 10x faster than Qwen3-VL → +3.8% F1 on LVIS, accuracy up, not down → 3B params, runs on one consumer GPU Treating the box as one unit keeps its coordinates tied together, which is why accuracy climbed instead of falling. One model handles detection, GUI grounding, OCR, and document understanding, ready for computer-use agents, robotics, and document pipelines. 100% open source, weights, code, demo, and paper all live.

NVIDIA just made AI detect objects 10x faster by deleting one step. It's called LocateAnything, and it removes the biggest bottleneck no one else was fixing in vision-language models. Normally a model builds each bounding box one coordinate token at a time. 100 objects means thousands of tokens before an answer. NVIDIA scrapped that: their Parallel Box Decoding predicts the whole box in a single forward pass, as one atomic unit. → 12.7 boxes/sec on one H100 → 10x faster than Qwen3-VL → +3.8% F1 on LVIS, accuracy up, not down → 3B params, runs on one consumer GPU Treating the box as one unit keeps its coordinates tied together, which is why accuracy climbed instead of falling. One model handles detection, GUI grounding, OCR, and document understanding, ready for computer-use agents, robotics, and document pipelines. 100% open source, weights, code, demo, and paper all live.

Alvaro Cintas

201,595 次观看 • 1 个月前

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

John McBride

150,334 次观看 • 5 个月前

A CHINESE GUY PUT 4 MINISFORUM MS-S1 MAX MINI PCs IN HIS BEDROOM AND TURNED THEM INTO A 24/7 AI AGENT CLUSTER. TOTAL POWER BILL: ABOUT $44/MO. each box is a tiny local AI workstation built around the Ryzen AI Max+ 395. around $3,000 per unit gets him 128GB of unified memory, 2TB storage, dual 10GbE, and up to roughly 96GB usable as VRAM on Linux. one MS-S1 Max can already run serious open models without touching the cloud. Qwen3-Coder 30B for fast coding, Llama 3.3 70B for heavier reasoning, and larger research models overnight when speed matters less than free inference. four boxes in one room changes the whole game. he is not opening a chatbot, paying for every loop, or shutting agents down before sleep. this is private infrastructure that keeps working even when he is offline. the agents can sort inboxes, review code, summarize documents, monitor feeds, prep meetings, and read papers overnight. on cloud APIs, that kind of always-on stack can easily burn $800 to $1,200 a month if used aggressively. his setup is roughly a $12,000 hardware spend, but the monthly cost is basically electricity. a rack, a switch, a NAS, a small monitor, and four tiny MS-S1 Max boxes turning a bedroom corner into a private inference factory. this is what AI looks like when it stops being rented and starts becoming something you own.

A CHINESE GUY PUT 4 MINISFORUM MS-S1 MAX MINI PCs IN HIS BEDROOM AND TURNED THEM INTO A 24/7 AI AGENT CLUSTER. TOTAL POWER BILL: ABOUT $44/MO. each box is a tiny local AI workstation built around the Ryzen AI Max+ 395. around $3,000 per unit gets him 128GB of unified memory, 2TB storage, dual 10GbE, and up to roughly 96GB usable as VRAM on Linux. one MS-S1 Max can already run serious open models without touching the cloud. Qwen3-Coder 30B for fast coding, Llama 3.3 70B for heavier reasoning, and larger research models overnight when speed matters less than free inference. four boxes in one room changes the whole game. he is not opening a chatbot, paying for every loop, or shutting agents down before sleep. this is private infrastructure that keeps working even when he is offline. the agents can sort inboxes, review code, summarize documents, monitor feeds, prep meetings, and read papers overnight. on cloud APIs, that kind of always-on stack can easily burn $800 to $1,200 a month if used aggressively. his setup is roughly a $12,000 hardware spend, but the monthly cost is basically electricity. a rack, a switch, a NAS, a small monitor, and four tiny MS-S1 Max boxes turning a bedroom corner into a private inference factory. this is what AI looks like when it stops being rented and starts becoming something you own.

Gipp 🦅

24,836 次观看 • 1 个月前

🚨BREAKING: Another video out of Houston, Texas shows ICE agents illegally boxing in a car on a public street… targeting U.S. citizens. Let’s be very clear about what ICE agents are doing… This is racial profiling. Reports out of Houston have already documented ICE agents surrounding vehicles, questioning U.S. citizens, and only backing off once they realize they are U.S. citizens. And in this video, you can literally watch the moment it falls apart… They walk away. They leave. They couldn’t take anyone because there was no crime. Because the only “reason” for the stop… was how those people looked. That’s illegal. The Constitution does not allow federal agents to box in your car, detain you, and demand proof of citizenship based on race, language, or appearance. That’s a violation of the Fourth Amendment. No warrant… no probable cause… no justification. Just racial profiling. This is exactly how constitutional rights get erased… not all at once, but in moments like this… where abuse happens, gets exposed, and no one is held accountable. And if they can do this to them… They can do this to anyone.

🚨BREAKING: Another video out of Houston, Texas shows ICE agents illegally boxing in a car on a public street… targeting U.S. citizens. Let’s be very clear about what ICE agents are doing… This is racial profiling. Reports out of Houston have already documented ICE agents surrounding vehicles, questioning U.S. citizens, and only backing off once they realize they are U.S. citizens. And in this video, you can literally watch the moment it falls apart… They walk away. They leave. They couldn’t take anyone because there was no crime. Because the only “reason” for the stop… was how those people looked. That’s illegal. The Constitution does not allow federal agents to box in your car, detain you, and demand proof of citizenship based on race, language, or appearance. That’s a violation of the Fourth Amendment. No warrant… no probable cause… no justification. Just racial profiling. This is exactly how constitutional rights get erased… not all at once, but in moments like this… where abuse happens, gets exposed, and no one is held accountable. And if they can do this to them… They can do this to anyone.

Jesus Freakin Congress

32,512 次观看 • 4 个月前

you can run claude code inside antigravity completely Free with zero credit card and no rate limits 😳 use openrouter’s free models + antigravity. no anthropic bill. no paid api keys. takes 10 minutes to set up. what you get during this setup: - full claude code agent experience - strong coding models (including deepseek-r1, qwen2.5-coder, llama-4, grok-4 free tier) - antigravity’s clean workspace and sandbox - unlimited usage (as long as you stay on free models) - easy model swapping - zero cost full setup guide (100% free): step 1: install antigravity -go to and install it -create a new workspace step 2: install claude code - inside antigravity, install the claude code extension from the marketplace - open the built-in terminal step 3: create openrouter free account -go to - sign up with google (no card needed) - go to keys and create a new api key step 4: set the environment variables -in antigravity terminal run: export ANTHROPIC_API_KEY=sk-or-xxx export OPENROUTER_API_KEY=sk-or-xxx step 5: launch claude code with free model -run this command: claude-code --model deepseek/deepseek-r1:free or try: qwen/qwen2.5-coder:free if you already have antigravity? skip straight to step 2. after 10 minutes you’ll have a full agentic coding setup running for free. this is currently one of the cheapest ways to run serious coding agents in 2026. bookmark this before they limit the free models.

you can run claude code inside antigravity completely Free with zero credit card and no rate limits 😳 use openrouter’s free models + antigravity. no anthropic bill. no paid api keys. takes 10 minutes to set up. what you get during this setup: - full claude code agent experience - strong coding models (including deepseek-r1, qwen2.5-coder, llama-4, grok-4 free tier) - antigravity’s clean workspace and sandbox - unlimited usage (as long as you stay on free models) - easy model swapping - zero cost full setup guide (100% free): step 1: install antigravity -go to and install it -create a new workspace step 2: install claude code - inside antigravity, install the claude code extension from the marketplace - open the built-in terminal step 3: create openrouter free account -go to - sign up with google (no card needed) - go to keys and create a new api key step 4: set the environment variables -in antigravity terminal run: export ANTHROPIC_API_KEY=sk-or-xxx export OPENROUTER_API_KEY=sk-or-xxx step 5: launch claude code with free model -run this command: claude-code --model deepseek/deepseek-r1:free or try: qwen/qwen2.5-coder:free if you already have antigravity? skip straight to step 2. after 10 minutes you’ll have a full agentic coding setup running for free. this is currently one of the cheapest ways to run serious coding agents in 2026. bookmark this before they limit the free models.

painn

32,057 次观看 • 2 个月前

Run Gemma 4 26B MoE on 8GB VRAM with 250k context at 20+ tokens/sec If you own any 8GB VRAM graphics card, stop what you are doing. Local AI just had its absolute "Holy Shit" moment for budget hardware. Yesterday, I benchmarked Unsloth Gemma 4 12B Q4_K_XL on an 8GB card. The community went wild but immediately demanded more: "Can we run a 25B+ model on budget GPUs?" Today, I’m delivering exactly that. I am running a massive 26B parameter Mixture of Experts (MoE) model locally on a standard 8GB VRAM setup with 250k full native context!. If you own an RTX 3060, 3070, 4060, or any budget GPU with 8GB of VRAM, the local AI paradigm has completely changed. The performance metrics are astonishing: - 20 tokens/sec flat decode throughput. - Stable, flat decode speed even with massive prompts. - I threw a 60k token prompt at it, and it still clocked in at 20 TPS without dropping a single frame. # What about prefill? Yes, Time To First Token (TTFT) is slightly high when swallowing massive contexts. But with a solid 200 tokens/sec prefill speed, the wait is barely noticeable and highly usable. And this is running completely without Multi Token Prediction (MTP) active. How is this possible? It’s the magic of Google's new QAT (Quantization Aware Training) quants for Gemma 4. The model weight file (unsloth gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf) is only 13.2 GB, making it the ultimate local powerhouse. # The Test Setup: CPU: Intel Core i7 RAM: 16GB System RAM GPU: NVIDIA GeForce RTX 4060 Laptop GPU (8GB VRAM) # The Secret Sauce (The -cmoe Flag) To make this work properly on any 8GB card, you must use the -cmoe (CPU MoE) flag in llama.cpp. This flag isolates the heavy MoE expert weights directly to system memory (CPU/RAM) while letting your GPU focus strictly on the Attention layers and the KV Cache. It prevents VRAM spillage and holds the throughput rock solid. # The flags: -m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v Once running, just open the UI on localhost and toggle the new reasoning lightbulb icon in the text input box to watch the model perform multi step thinking. Are you still running smaller models, or are you ready to scale up your budget local setups? Let's discuss in the replies

Run Gemma 4 26B MoE on 8GB VRAM with 250k context at 20+ tokens/sec If you own any 8GB VRAM graphics card, stop what you are doing. Local AI just had its absolute "Holy Shit" moment for budget hardware. Yesterday, I benchmarked Unsloth Gemma 4 12B Q4_K_XL on an 8GB card. The community went wild but immediately demanded more: "Can we run a 25B+ model on budget GPUs?" Today, I’m delivering exactly that. I am running a massive 26B parameter Mixture of Experts (MoE) model locally on a standard 8GB VRAM setup with 250k full native context!. If you own an RTX 3060, 3070, 4060, or any budget GPU with 8GB of VRAM, the local AI paradigm has completely changed. The performance metrics are astonishing: - 20 tokens/sec flat decode throughput. - Stable, flat decode speed even with massive prompts. - I threw a 60k token prompt at it, and it still clocked in at 20 TPS without dropping a single frame. # What about prefill? Yes, Time To First Token (TTFT) is slightly high when swallowing massive contexts. But with a solid 200 tokens/sec prefill speed, the wait is barely noticeable and highly usable. And this is running completely without Multi Token Prediction (MTP) active. How is this possible? It’s the magic of Google's new QAT (Quantization Aware Training) quants for Gemma 4. The model weight file (unsloth gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf) is only 13.2 GB, making it the ultimate local powerhouse. # The Test Setup: CPU: Intel Core i7 RAM: 16GB System RAM GPU: NVIDIA GeForce RTX 4060 Laptop GPU (8GB VRAM) # The Secret Sauce (The -cmoe Flag) To make this work properly on any 8GB card, you must use the -cmoe (CPU MoE) flag in llama.cpp. This flag isolates the heavy MoE expert weights directly to system memory (CPU/RAM) while letting your GPU focus strictly on the Attention layers and the KV Cache. It prevents VRAM spillage and holds the throughput rock solid. # The flags: -m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v Once running, just open the UI on localhost and toggle the new reasoning lightbulb icon in the text input box to watch the model perform multi step thinking. Are you still running smaller models, or are you ready to scale up your budget local setups? Let's discuss in the replies

Alok

292,770 次观看 • 2 个月前

Hello Midnight🅓🅡🅔🅐🅜🅔🅡 let me quickly share from my perspective as well~ 1. During Food Support, there are so many boxes coming. Not only come for JoongDunk or staff, but from all cast fanbases as well. So it’s really important to differentiate each box clearly to avoid confusion. There are a lot of time, Artist/Staff don’t have decent time to eat so they need to grab the food fast so it’s actually what’s advised- minimizing human error. (You can see other Artist are also putting their stickers individually). I know it maybe everyone’s first time in sending food support, it’s shocking and hectic at the same time. So i understand the frustration as you only want to rely support for both. So what i can advise you, you can add on SHARE BOX. There you can send message for Staff or even Dunk (if you send from JOT, sorry it was written in Thai for staff Summer Night at that time) 2. Each of fanbase is given the rights to send food support and to avoid unnecessary food waste, it’s not advised to send for both from one fanbase all the time. There are many times, since Joong and Dunk appreciate fans food support but cant finish them and they have to bring it home (Joong’s mom sometimes share about this or sometimes i saw managers bring their food support box to their cars). But not all the time, they can bring it home, right? Especially if the shooting take the whole day. Other than our food supporty, there are also food provide from other fanbase and also mandatory provided from the company. So always try to discuss with official~ If somehow you are looking for sending both JoongDunk, i advised sending Food Truck instead (if possible, though the cue is as rare as gem). Usually Food Truck is advised to send as CP Project (that’s at least from what i experience from THK) >> Since we have so many cast during DYTD, let’s wait for official consideration. Feel free to join whenever your heart is happy~ 3. I hope this doesn’t discourage you in doing anything for JoongDunk. Your concern is matter and thank you for advising it. There are still many things you can do to support them, feel free to ask me if you need some advise ❤️

Hello Midnight🅓🅡🅔🅐🅜🅔🅡 let me quickly share from my perspective as well~ 1. During Food Support, there are so many boxes coming. Not only come for JoongDunk or staff, but from all cast fanbases as well. So it’s really important to differentiate each box clearly to avoid confusion. There are a lot of time, Artist/Staff don’t have decent time to eat so they need to grab the food fast so it’s actually what’s advised- minimizing human error. (You can see other Artist are also putting their stickers individually). I know it maybe everyone’s first time in sending food support, it’s shocking and hectic at the same time. So i understand the frustration as you only want to rely support for both. So what i can advise you, you can add on SHARE BOX. There you can send message for Staff or even Dunk (if you send from JOT, sorry it was written in Thai for staff Summer Night at that time) 2. Each of fanbase is given the rights to send food support and to avoid unnecessary food waste, it’s not advised to send for both from one fanbase all the time. There are many times, since Joong and Dunk appreciate fans food support but cant finish them and they have to bring it home (Joong’s mom sometimes share about this or sometimes i saw managers bring their food support box to their cars). But not all the time, they can bring it home, right? Especially if the shooting take the whole day. Other than our food supporty, there are also food provide from other fanbase and also mandatory provided from the company. So always try to discuss with official~ If somehow you are looking for sending both JoongDunk, i advised sending Food Truck instead (if possible, though the cue is as rare as gem). Usually Food Truck is advised to send as CP Project (that’s at least from what i experience from THK) >> Since we have so many cast during DYTD, let’s wait for official consideration. Feel free to join whenever your heart is happy~ 3. I hope this doesn’t discourage you in doing anything for JoongDunk. Your concern is matter and thank you for advising it. There are still many things you can do to support them, feel free to ask me if you need some advise ❤️

𝑀𝒶𝓇❣️#DareYouToDeath

18,951 次观看 • 8 个月前

This guy built a mini AI farm out of 4 Nvidia boxes It does not look like a data center. It looks like a stack of small machines sitting next to a laptop. But each box is a DGX Spark with Grace Blackwell inside, 128GB unified memory, and enough room to run models normal gaming GPUs cannot even open. Using the launch price from the article, 4 of them is almost $12,000 of local AI compute on one desk. That sounds expensive until you compare it to cloud GPUs. A serious AI builder can burn $1,500 to $3,000 a month renting A100s and H100s for client work, fine-tunes, agents and 70B models. He basically moved that bill from the cloud into hardware he owns. 4 Nvidia boxes. 512GB unified memory. No hourly meter running in the background. No rented GPUs eating the margin every time an agent runs too long. The funny part is most people still think local AI means a slow laptop running a toy model. Meanwhile guys like this are stacking compute at home. Save this, local AI is turning into the new mining farm.

This guy built a mini AI farm out of 4 Nvidia boxes It does not look like a data center. It looks like a stack of small machines sitting next to a laptop. But each box is a DGX Spark with Grace Blackwell inside, 128GB unified memory, and enough room to run models normal gaming GPUs cannot even open. Using the launch price from the article, 4 of them is almost $12,000 of local AI compute on one desk. That sounds expensive until you compare it to cloud GPUs. A serious AI builder can burn $1,500 to $3,000 a month renting A100s and H100s for client work, fine-tunes, agents and 70B models. He basically moved that bill from the cloud into hardware he owns. 4 Nvidia boxes. 512GB unified memory. No hourly meter running in the background. No rented GPUs eating the margin every time an agent runs too long. The funny part is most people still think local AI means a slow laptop running a toy model. Meanwhile guys like this are stacking compute at home. Save this, local AI is turning into the new mining farm.

Gipp 🦅

591,167 次观看 • 2 个月前

Introducing the Agent Virtual Machine (AVM) Think V8 for agents. AI agents are currently running on your computer with no unified security, no resource limits, and no visibility into what data they're sending out. Every agent framework builds its own security model, its own sandboxing, its own permission system. You configure each one separately. You audit each one separately. You hope you didn't miss anything in any of them. The AVM changes this. It's a single runtime daemon (avmd) that sits between every agent framework and your operating system. Install it once, configure one policy file, and every agent on your machine runs inside it - regardless of which framework built it. The AVM enforces security (91-pattern injection scanner, tool/file/network ACLs, approval prompts), protects your privacy (classifies every outbound byte for PII, credentials, and financial data - blocks or alerts in real-time), and governs resources (you say "50% CPU, 4GB RAM" and the AVM fair-shares it across all agents, halting any that exceed their budget). One config. One audit command. One kill switch. The architectural model is V8 for agents. Chrome, Node.js, and Deno are different products but they share V8 as their execution engine. Agent frameworks bring the UX. The AVM brings the trust. Where needed, AVM can also generate zero-knowledge proofs of agent execution via 25 purpose-built opcodes and 6 proof systems, providing the foundational pillar for the agent-to-agent economy. AVM v0.1.0 - Changelog - Security gate: 5-layer injection scanner with 91 compiled regex patterns. Every input and output scanned. Fail-closed - nothing passes without clearing the gate. - Privacy layer: Classifies all outbound data for PII, credentials, and financial info (27 detection patterns + Luhn validation). Block, ask, warn, or allow per category. Tamper-evident hash-chained log of every egress event. - Resource governor: User sets system-wide caps (CPU/memory/disk/network). AVM fair-shares across all agents. Gas budget per agent - when gas runs out, execution halts. No agent starves your machine. - Sandbox execution: Real code execution in isolated process sandboxes (rlimits, env sanitization) or Docker containers (--cap-drop ALL, --network none, --read-only). AVM auto-selects the tier - agents never choose their own sandbox. - Approval flow: Dangerous operations (file writes, shell commands, network requests) trigger interactive approval prompts. 5-minute timeout auto-denies. Every decision logged. - CLI dashboard: hyperspace-avm top shows all running agents, resource usage, gas budgets, security events, and privacy stats in one live-updating screen. - Node.js SDK: Zero-dependency hyperspace/avm package. AVM.tryConnect() for graceful fallback - if avmd isn't running, the agent framework uses its own execution path. OpenClaw adapter example included. - One config for all agents: ~/.hyperspace/avm-policy.json governs every agent framework on your machine. One file. One audit. One kill switch.

Introducing the Agent Virtual Machine (AVM) Think V8 for agents. AI agents are currently running on your computer with no unified security, no resource limits, and no visibility into what data they're sending out. Every agent framework builds its own security model, its own sandboxing, its own permission system. You configure each one separately. You audit each one separately. You hope you didn't miss anything in any of them. The AVM changes this. It's a single runtime daemon (avmd) that sits between every agent framework and your operating system. Install it once, configure one policy file, and every agent on your machine runs inside it - regardless of which framework built it. The AVM enforces security (91-pattern injection scanner, tool/file/network ACLs, approval prompts), protects your privacy (classifies every outbound byte for PII, credentials, and financial data - blocks or alerts in real-time), and governs resources (you say "50% CPU, 4GB RAM" and the AVM fair-shares it across all agents, halting any that exceed their budget). One config. One audit command. One kill switch. The architectural model is V8 for agents. Chrome, Node.js, and Deno are different products but they share V8 as their execution engine. Agent frameworks bring the UX. The AVM brings the trust. Where needed, AVM can also generate zero-knowledge proofs of agent execution via 25 purpose-built opcodes and 6 proof systems, providing the foundational pillar for the agent-to-agent economy. AVM v0.1.0 - Changelog - Security gate: 5-layer injection scanner with 91 compiled regex patterns. Every input and output scanned. Fail-closed - nothing passes without clearing the gate. - Privacy layer: Classifies all outbound data for PII, credentials, and financial info (27 detection patterns + Luhn validation). Block, ask, warn, or allow per category. Tamper-evident hash-chained log of every egress event. - Resource governor: User sets system-wide caps (CPU/memory/disk/network). AVM fair-shares across all agents. Gas budget per agent - when gas runs out, execution halts. No agent starves your machine. - Sandbox execution: Real code execution in isolated process sandboxes (rlimits, env sanitization) or Docker containers (--cap-drop ALL, --network none, --read-only). AVM auto-selects the tier - agents never choose their own sandbox. - Approval flow: Dangerous operations (file writes, shell commands, network requests) trigger interactive approval prompts. 5-minute timeout auto-denies. Every decision logged. - CLI dashboard: hyperspace-avm top shows all running agents, resource usage, gas budgets, security events, and privacy stats in one live-updating screen. - Node.js SDK: Zero-dependency hyperspace/avm package. AVM.tryConnect() for graceful fallback - if avmd isn't running, the agent framework uses its own execution path. OpenClaw adapter example included. - One config for all agents: ~/.hyperspace/avm-policy.json governs every agent framework on your machine. One file. One audit. One kill switch.

Varun

142,713 次观看 • 4 个月前

"npx t3 connect" This one's been a lot of work. You can now set up remote control for T3 Code on any internet-connected box with literally one command. All for free. T3 Connect is a minimal open source tunnel layer allowing you to control T3 Code instances remotely without needing Tailscale set up. I've been daily driving it for a month and it has changed how I code. Julius and I put a lot of effort into making setup as smooth as possible. Step 1: Install Claude Code, Codex, OpenCode, or Grok Build Step 2: Run "npx t3 connect" Step 3: Click link and sign in Step 4: You can now control that computer on T3 Code web, desktop or mobile (dropping very soon) We are currently providing this for free (s/o CloudFlare for bumping our tunnel limits). Every user can connect up to 3 devices. We don't want to charge for this, but if the bill gets unacceptable we may have to change course. If you hit limits or have issues, you can always fork, self host, or use Tailscale. T3 Connect may seem like a small ergonomic win. Tbh that's exactly what it is. Regardless, it's one I'm really proud of.

"npx t3 connect" This one's been a lot of work. You can now set up remote control for T3 Code on any internet-connected box with literally one command. All for free. T3 Connect is a minimal open source tunnel layer allowing you to control T3 Code instances remotely without needing Tailscale set up. I've been daily driving it for a month and it has changed how I code. Julius and I put a lot of effort into making setup as smooth as possible. Step 1: Install Claude Code, Codex, OpenCode, or Grok Build Step 2: Run "npx t3 connect" Step 3: Click link and sign in Step 4: You can now control that computer on T3 Code web, desktop or mobile (dropping very soon) We are currently providing this for free (s/o CloudFlare for bumping our tunnel limits). Every user can connect up to 3 devices. We don't want to charge for this, but if the bill gets unacceptable we may have to change course. If you hit limits or have issues, you can always fork, self host, or use Tailscale. T3 Connect may seem like a small ergonomic win. Tbh that's exactly what it is. Regardless, it's one I'm really proud of.

Theo - t3.gg

306,822 次观看 • 17 天前

I had the same thought so I've been playing with it in nanochat. E.g. here's 8 agents (4 claude, 4 codex), with 1 GPU each running nanochat experiments (trying to delete logit softcap without regression). The TLDR is that it doesn't work and it's a mess... but it's still very pretty to look at :) I tried a few setups: 8 independent solo researchers, 1 chief scientist giving work to 8 junior researchers, etc. Each research program is a git branch, each scientist forks it into a feature branch, git worktrees for isolation, simple files for comms, skip Docker/VMs for simplicity atm (I find that instructions are enough to prevent interference). Research org runs in tmux window grids of interactive sessions (like Teams) so that it's pretty to look at, see their individual work, and "take over" if needed, i.e. no -p. But ok the reason it doesn't work so far is that the agents' ideas are just pretty bad out of the box, even at highest intelligence. They don't think carefully though experiment design, they run a bit non-sensical variations, they don't create strong baselines and ablate things properly, they don't carefully control for runtime or flops. (just as an example, an agent yesterday "discovered" that increasing the hidden size of the network improves the validation loss, which is a totally spurious result given that a bigger network will have a lower validation loss in the infinite data regime, but then it also trains for a lot longer, it's not clear why I had to come in to point that out). They are very good at implementing any given well-scoped and described idea but they don't creatively generate them. But the goal is that you are now programming an organization (e.g. a "research org") and its individual agents, so the "source code" is the collection of prompts, skills, tools, etc. and processes that make it up. E.g. a daily standup in the morning is now part of the "org code". And optimizing nanochat pretraining is just one of the many tasks (almost like an eval). Then - given an arbitrary task, how quickly does your research org generate progress on it?

I had the same thought so I've been playing with it in nanochat. E.g. here's 8 agents (4 claude, 4 codex), with 1 GPU each running nanochat experiments (trying to delete logit softcap without regression). The TLDR is that it doesn't work and it's a mess... but it's still very pretty to look at :) I tried a few setups: 8 independent solo researchers, 1 chief scientist giving work to 8 junior researchers, etc. Each research program is a git branch, each scientist forks it into a feature branch, git worktrees for isolation, simple files for comms, skip Docker/VMs for simplicity atm (I find that instructions are enough to prevent interference). Research org runs in tmux window grids of interactive sessions (like Teams) so that it's pretty to look at, see their individual work, and "take over" if needed, i.e. no -p. But ok the reason it doesn't work so far is that the agents' ideas are just pretty bad out of the box, even at highest intelligence. They don't think carefully though experiment design, they run a bit non-sensical variations, they don't create strong baselines and ablate things properly, they don't carefully control for runtime or flops. (just as an example, an agent yesterday "discovered" that increasing the hidden size of the network improves the validation loss, which is a totally spurious result given that a bigger network will have a lower validation loss in the infinite data regime, but then it also trains for a lot longer, it's not clear why I had to come in to point that out). They are very good at implementing any given well-scoped and described idea but they don't creatively generate them. But the goal is that you are now programming an organization (e.g. a "research org") and its individual agents, so the "source code" is the collection of prompts, skills, tools, etc. and processes that make it up. E.g. a daily standup in the morning is now part of the "org code". And optimizing nanochat pretraining is just one of the many tasks (almost like an eval). Then - given an arbitrary task, how quickly does your research org generate progress on it?

Andrej Karpathy

1,648,015 次观看 • 5 个月前

Right now, you may not have access to models like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.

Right now, you may not have access to models like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.

Alok

65,387 次观看 • 1 个月前

Stateless History Node is almost like a regular Ethereum node, but it doesn't store state and it doesn't have EVM execution. It's used only for syncing events and thus - is faster and gives you FREE INDEXING. You don't have to pay 6 figures for RPC anymore! Just spin up a Stateless History Node, plug rindexer or Ponder there, and enjoy free (AND FAST!!) indexing! This node is syncing >1000 blocks per second at my local pc (less than 6hrs for the whole Ethereum), and it should use less than 200GB - which means you can host it on a MacMini, Hetzner or whatever. You can futhermore filter that by using block ranges or bloom filters, etc - I haven't developed this yet. What you see is a proof of concept. It works via native devp2p 'eth' protocol, but with EIP4444 and The Prune we would have to also support era1 archives and Portal Network. But so far it works - there are plenty of peers serving historical receipts, and they serve them FAST! If you run Stateless History Node you can also serve the blocks and receipts - so that could help to preserve archival data too. For now there is no data validation yet (and even no data storage - that's a very early PoC), but we can verify validity of chain by simultaneously running a lightweight CL node (or not lightweight if you're extremely paranoid). And then support verifying the hashes of receipts and blocks with their parents, maintaining full integrity and zero trust. It's also written in rust, btw. So, I guess, at least for Ethereum Mainnet the era of RPC's pumping moneybags is over - there's finally a local, trustless and free indexing alternative available. Too sad this won't work for Optimism / Base , cause despite introducing P2P after Bedrock - they haven't enabled receipts transfer in the protocol (or at least I couldn't find one). Arbitrum is even sadder - I don't believe there is a P2P layer at all - you just have to run your own node, hold state and execute blocks to get events. There is hope - Paradigm recently released Ress - stateless execution, but it requires nodes to support Witness preparation & exchange - but this could work for L2s - cause the main blocker for local RPCs rn is huge state (VPS with TB storage cost a lot), and the second blocker is EVM forks makes it hard to hold a node - it needs to be maintained, upgraded, etc. Ress at least solves the state part. But anyways, I will try to continue working on this and release some MVP version with RPC endpoint and data storage soon - follow the updates!

Stateless History Node is almost like a regular Ethereum node, but it doesn't store state and it doesn't have EVM execution. It's used only for syncing events and thus - is faster and gives you FREE INDEXING. You don't have to pay 6 figures for RPC anymore! Just spin up a Stateless History Node, plug rindexer or Ponder there, and enjoy free (AND FAST!!) indexing! This node is syncing >1000 blocks per second at my local pc (less than 6hrs for the whole Ethereum), and it should use less than 200GB - which means you can host it on a MacMini, Hetzner or whatever. You can futhermore filter that by using block ranges or bloom filters, etc - I haven't developed this yet. What you see is a proof of concept. It works via native devp2p 'eth' protocol, but with EIP4444 and The Prune we would have to also support era1 archives and Portal Network. But so far it works - there are plenty of peers serving historical receipts, and they serve them FAST! If you run Stateless History Node you can also serve the blocks and receipts - so that could help to preserve archival data too. For now there is no data validation yet (and even no data storage - that's a very early PoC), but we can verify validity of chain by simultaneously running a lightweight CL node (or not lightweight if you're extremely paranoid). And then support verifying the hashes of receipts and blocks with their parents, maintaining full integrity and zero trust. It's also written in rust, btw. So, I guess, at least for Ethereum Mainnet the era of RPC's pumping moneybags is over - there's finally a local, trustless and free indexing alternative available. Too sad this won't work for Optimism / Base , cause despite introducing P2P after Bedrock - they haven't enabled receipts transfer in the protocol (or at least I couldn't find one). Arbitrum is even sadder - I don't believe there is a P2P layer at all - you just have to run your own node, hold state and execute blocks to get events. There is hope - Paradigm recently released Ress - stateless execution, but it requires nodes to support Witness preparation & exchange - but this could work for L2s - cause the main blocker for local RPCs rn is huge state (VPS with TB storage cost a lot), and the second blocker is EVM forks makes it hard to hold a node - it needs to be maintained, upgraded, etc. Ress at least solves the state part. But anyways, I will try to continue working on this and release some MVP version with RPC endpoint and data storage soon - follow the updates!

Convergence Boy

28,877 次观看 • 7 个月前

While many around the league don’t expect any linebackers to be drafted tonight, if there is one, it certainly could be #TexasAM’s Edgerrin Cooper. Cooper is the most complete LB in the 2024 draft class. He’s shown to be: 1️⃣an elite athlete 2️⃣a consistent and impactful run defender 3️⃣a capable and efficient blitzer, and 4️⃣able to use his size and bend to disrupt in pass protection As a run defender, he finished with an 87.6 PFF grade, highest among any expected draft linebackers in this year’s draft class. That includes 15 TFLs or no gain plays. As you can see (🎥), his downhill force plus balance and control allows him to consistently win in the run game As a pass rusher, he had 7 sacks on the year, 4 of which came from playing on the line of scrimmage. When lined up on the line of scrimmage, he generated a pressure on over 30% of his pass rush snaps. Elite ‼️ And in coverage, he finished with a top-10 coverage grade int eh country last season (per PFF College) among LBs lined up in the box. He’s able to use his length and bend, along with developed vision and timing to disrupt plays from the box. Couple all of that with a 4.51 forty time and would-be impressive athletic testing numbers if he was 100% for the draft process (why he wasn’t able to officially go every day in practice at East-West Shrine Bowl), and it’s hard to ignore his NFL starting potential. There’s a real chance he goes in late round one, but if he’s there on Day 2, he may not only be one of, if not the, first linebacker drafted, but may be one of the first players taken on Day 2 of the draft. #ShrineBowlWhosNext

While many around the league don’t expect any linebackers to be drafted tonight, if there is one, it certainly could be #TexasAM’s Edgerrin Cooper. Cooper is the most complete LB in the 2024 draft class. He’s shown to be: 1️⃣an elite athlete 2️⃣a consistent and impactful run defender 3️⃣a capable and efficient blitzer, and 4️⃣able to use his size and bend to disrupt in pass protection As a run defender, he finished with an 87.6 PFF grade, highest among any expected draft linebackers in this year’s draft class. That includes 15 TFLs or no gain plays. As you can see (🎥), his downhill force plus balance and control allows him to consistently win in the run game As a pass rusher, he had 7 sacks on the year, 4 of which came from playing on the line of scrimmage. When lined up on the line of scrimmage, he generated a pressure on over 30% of his pass rush snaps. Elite ‼️ And in coverage, he finished with a top-10 coverage grade int eh country last season (per PFF College) among LBs lined up in the box. He’s able to use his length and bend, along with developed vision and timing to disrupt plays from the box. Couple all of that with a 4.51 forty time and would-be impressive athletic testing numbers if he was 100% for the draft process (why he wasn’t able to officially go every day in practice at East-West Shrine Bowl), and it’s hard to ignore his NFL starting potential. There’s a real chance he goes in late round one, but if he’s there on Day 2, he may not only be one of, if not the, first linebacker drafted, but may be one of the first players taken on Day 2 of the draft. #ShrineBowlWhosNext

Eric Galko

100,408 次观看 • 2 年前

Enter the Wild: Ape Fortune Collection, Free Mint on 26th June! Ape Fortune Collection - 777 NFTs grants holders access to unique benefits and rewards at the heart of the Bored Slot ecosystem. Where Only the Brave Dare! 🎰Game Summary: Bored Slot redefines online gaming by combining the thrill of live slots with a dynamic token ecosystem. The unique 'Play, Earn, Mine' model leverages Banana Points, enabling apes to unlock new levels and mine $SPC and tokens, enhancing rewards! 🐒Holder Utilities: 1. Exclusive Access: Enhanced gameplay with special access to high-tier slots. 2. Greater Rewards: Amp up with powerful gameplay multipliers for higher potential earnings. 3. IRL Perks: Score VIP event invites and exclusive merch—only for NFT holders. 🎁Loot Box: Exclusive in-game treasures acquired during spins, act as wild cards, boosting your gameplay and stacking up until a special reveal date. Each box accumulates and opens to award substantial Banana points, Merchandises and Game Credits! 🔓NFT Perks: Phase 1 - Normal, Rare, Legendary Tiers: Each tier unlocks distinct slot experiences. - Loot Boxes tied to NFTs: They're yours even if traded, enhancing your NFT’s value in the secondary market - Boost Your Gameplay: Banana points accumulated daily to your Bored Slot account! And of course, tiers matter! 🌟Future Enhancements and Considerations: - NFT Holder + Ape Club Owner Boost: Potential for increased Gross Gaming Revenue (GGR) in future phases. - Game Multipliers: Maximize your Banana Points farming by holding the NFT! Owning an Ape Fortune NFT is akin to holding the key to a hidden treasure trove. These Banana NFTs unlock a world of unique benefits and rewards, transforming the Bored Slot experience into a primate paradise. Mint Details: Price - FREE Supply - 777 Date - 26 June 2024, 9pm SGT Chain - ETH Hammer that '🍌' below, you legendary Apes! Ignite the mayhem!

Enter the Wild: Ape Fortune Collection, Free Mint on 26th June! Ape Fortune Collection - 777 NFTs grants holders access to unique benefits and rewards at the heart of the Bored Slot ecosystem. Where Only the Brave Dare! 🎰Game Summary: Bored Slot redefines online gaming by combining the thrill of live slots with a dynamic token ecosystem. The unique 'Play, Earn, Mine' model leverages Banana Points, enabling apes to unlock new levels and mine $SPC and tokens, enhancing rewards! 🐒Holder Utilities: 1. Exclusive Access: Enhanced gameplay with special access to high-tier slots. 2. Greater Rewards: Amp up with powerful gameplay multipliers for higher potential earnings. 3. IRL Perks: Score VIP event invites and exclusive merch—only for NFT holders. 🎁Loot Box: Exclusive in-game treasures acquired during spins, act as wild cards, boosting your gameplay and stacking up until a special reveal date. Each box accumulates and opens to award substantial Banana points, Merchandises and Game Credits! 🔓NFT Perks: Phase 1 - Normal, Rare, Legendary Tiers: Each tier unlocks distinct slot experiences. - Loot Boxes tied to NFTs: They're yours even if traded, enhancing your NFT’s value in the secondary market - Boost Your Gameplay: Banana points accumulated daily to your Bored Slot account! And of course, tiers matter! 🌟Future Enhancements and Considerations: - NFT Holder + Ape Club Owner Boost: Potential for increased Gross Gaming Revenue (GGR) in future phases. - Game Multipliers: Maximize your Banana Points farming by holding the NFT! Owning an Ape Fortune NFT is akin to holding the key to a hidden treasure trove. These Banana NFTs unlock a world of unique benefits and rewards, transforming the Bored Slot experience into a primate paradise. Mint Details: Price - FREE Supply - 777 Date - 26 June 2024, 9pm SGT Chain - ETH Hammer that '🍌' below, you legendary Apes! Ignite the mayhem!

Bored Slot Official

17,611 次观看 • 2 年前

this is worth more than most five figure courses 16 claude agents audit an entire repo at once, a second fleet re-checks every finding on fresh context, and the whole thing runs off one diagram instead of a prompt i ran it against my own code and got back 11 endpoints where i never checked who was logged in, 3 of which the verifier threw out before they ever reached me this is Graph Engineering, the layer above prompting, and it runs on the agent you already pay for: - write your plan out, then ask one question at every "and then": does the next step actually read what the previous one produced - the seams that fail that question were never dependencies, so those jobs run at the same time - the arrows that survive are your real edges, and the longest chain of them is your floor that no number of agents shortens - want it faster, cut a false edge instead of adding a worker - fan the independent work out, one agent per item, no shared state between them - send every finding to a separate agent on fresh context, because a model recognises its own writing 73.5% of the time and grades it kinder once it does - make that verifier check a real signal like a passing test, never the worker's own word that it finished - shard the fleet across worktrees so parallel workers stop overwriting each other, one rule frozen into every worker: never git stash, never git reset - merge only what came back verified, into one report instead of twenty open chats the catch is the ceiling. at 95% independent work 16 agents return 9.14x rather than the 16 you would guess, and even 256 only reach 18.6x, because the merge and the verify stay serial however wide you fan coordination itself is free plain code and every agent underneath it is billed, so start at twenty files and widen once it works bookmark this, the whole method with all six ready-to-run graphs is written out in the article ↓

this is worth more than most five figure courses 16 claude agents audit an entire repo at once, a second fleet re-checks every finding on fresh context, and the whole thing runs off one diagram instead of a prompt i ran it against my own code and got back 11 endpoints where i never checked who was logged in, 3 of which the verifier threw out before they ever reached me this is Graph Engineering, the layer above prompting, and it runs on the agent you already pay for: - write your plan out, then ask one question at every "and then": does the next step actually read what the previous one produced - the seams that fail that question were never dependencies, so those jobs run at the same time - the arrows that survive are your real edges, and the longest chain of them is your floor that no number of agents shortens - want it faster, cut a false edge instead of adding a worker - fan the independent work out, one agent per item, no shared state between them - send every finding to a separate agent on fresh context, because a model recognises its own writing 73.5% of the time and grades it kinder once it does - make that verifier check a real signal like a passing test, never the worker's own word that it finished - shard the fleet across worktrees so parallel workers stop overwriting each other, one rule frozen into every worker: never git stash, never git reset - merge only what came back verified, into one report instead of twenty open chats the catch is the ceiling. at 95% independent work 16 agents return 9.14x rather than the 16 you would guess, and even 256 only reach 18.6x, because the merge and the verify stay serial however wide you fan coordination itself is free plain code and every agent underneath it is billed, so start at twenty files and widen once it works bookmark this, the whole method with all six ready-to-run graphs is written out in the article ↓

Argona

156,513 次观看 • 19 天前

Another WTF moment. A developer just open-sourced a coding agent harness that boots 245x faster than Claude Code. It's called jcode. You launch it and the first frame renders in 14 milliseconds. Claude Code takes 3,436. One active session uses 27.8 MB of RAM. Claude Code uses 386.6. Run ten sessions in parallel and jcode holds at 117 MB while OpenCode swells to 3.2 GB. Each agent has a semantic memory graph instead of a scratchpad. Every turn gets embedded as a vector. The graph is queried on every turn for related memories, and a sideagent verifies the hits before injecting them into context. Consolidation runs in the background to check for stale or conflicting facts. No manual /remember calls. No token burn on lookup tools. The provider list is 30+ deep. Claude, ChatGPT, Gemini, GitHub Copilot, Azure, OpenRouter, DeepSeek, Groq, Mistral, Perplexity, Fireworks, Ollama, LM Studio, and any OpenAI-compatible endpoint you point it at. Ran out of tokens on your first ChatGPT Pro sub? /account swaps to the second. Then there's Swarm. Spawn two agents in the same repo and the server manages them. When agent A edits a file agent B has been reading, agent B gets pinged and can check the diff. Agents can DM each other, broadcast to the room, or spawn their own worker teams for parallel tasks. Groups, channels, and completion statuses are handled automatically. The UI has live side panels that render mermaid diagrams inline. To make it fast, the author wrote a Rust mermaid renderer 1800x faster than the JavaScript one, then wrote a custom terminal called Handterm because no existing terminal could do smooth partial-line scrolling. Self-dev mode is where it gets wild. Tell your agent to enter self-dev and it starts editing jcode's own source code, rebuilds the binary, reloads it live, and keeps working across your existing sessions. You can also resume broken sessions from Claude Code, Codex, OpenCode, or pi directly inside jcode. Anthropic's cache goes cold at the 5-minute mark and you're staring down a big cache miss on your next turn? The UI warns you before you spend the tokens. Written in Rust. MIT licensed. Runs on macOS, Windows, Linux, and Termux. Sitting at 11.2k stars with a native iOS app coming.

Another WTF moment. A developer just open-sourced a coding agent harness that boots 245x faster than Claude Code. It's called jcode. You launch it and the first frame renders in 14 milliseconds. Claude Code takes 3,436. One active session uses 27.8 MB of RAM. Claude Code uses 386.6. Run ten sessions in parallel and jcode holds at 117 MB while OpenCode swells to 3.2 GB. Each agent has a semantic memory graph instead of a scratchpad. Every turn gets embedded as a vector. The graph is queried on every turn for related memories, and a sideagent verifies the hits before injecting them into context. Consolidation runs in the background to check for stale or conflicting facts. No manual /remember calls. No token burn on lookup tools. The provider list is 30+ deep. Claude, ChatGPT, Gemini, GitHub Copilot, Azure, OpenRouter, DeepSeek, Groq, Mistral, Perplexity, Fireworks, Ollama, LM Studio, and any OpenAI-compatible endpoint you point it at. Ran out of tokens on your first ChatGPT Pro sub? /account swaps to the second. Then there's Swarm. Spawn two agents in the same repo and the server manages them. When agent A edits a file agent B has been reading, agent B gets pinged and can check the diff. Agents can DM each other, broadcast to the room, or spawn their own worker teams for parallel tasks. Groups, channels, and completion statuses are handled automatically. The UI has live side panels that render mermaid diagrams inline. To make it fast, the author wrote a Rust mermaid renderer 1800x faster than the JavaScript one, then wrote a custom terminal called Handterm because no existing terminal could do smooth partial-line scrolling. Self-dev mode is where it gets wild. Tell your agent to enter self-dev and it starts editing jcode's own source code, rebuilds the binary, reloads it live, and keeps working across your existing sessions. You can also resume broken sessions from Claude Code, Codex, OpenCode, or pi directly inside jcode. Anthropic's cache goes cold at the 5-minute mark and you're staring down a big cache miss on your next turn? The UI warns you before you spend the tokens. Written in Rust. MIT licensed. Runs on macOS, Windows, Linux, and Termux. Sitting at 11.2k stars with a native iOS app coming.

Brady Long

204,606 次观看 • 18 天前

🪴 GT Protocol Monthly Recap: May 2026 May focused on launching advanced trading infrastructure, introducing AI risk-management tools, and shipping major platform upgrades. 🚀 Hyperliquid Vaults Live Run multiple algorithmic strategies on a single Hyperliquid Vault inside GT App. Enjoy automated execution, auto-rebalancing, and protocol-level security. You can find Vault trading on the Hyperliquid exchange account connection page in the Trade on Vault section. Try it in GT App 👉 🤖 AI Hedge Fund Experiment Live An experimental AI Hedge Fund powered by 5 independent LLM models is live on Hyperliquid. Each model manages $10,000 to test different AI trading personalities and allocation strategies. Discover it now here 👉 📈 Isolated Margin & AI Risk Tools Isolated Margin is live across GT App for precise risk management. Enhanced with AI-powered logic, it assists with dynamic asset monitoring and smarter strategy deployment. Try it in GT App 👉 🔥 Top Strategy Performance Top trader strategies like "lebakien" achieved over +141% profit this month. Users can explore metrics and follow the strategies of top traders directly in the marketplace. Explore Marketplace 👉 🛠 Key Product Updates ⚙️ Strategy Discovery: enhanced demo trading flows and top trader strategy integration. ⚙️ AI Strategy Chat: demoed a flow to create, launch, and test strategies via natural language chat. ⚙️ Advanced Execution: added manual safety orders for granular control over active positions. ⚙️ Testing & Validation: optimized historical data validation for more accurate strategy testing. ⚙️ Knowledge Hub: launched GT Protocol Learn and a new Knowledge Base for streamlined support. ⚙️ Performance: upgraded website structure and improved overall page responsiveness. Find all the latest GT App updates Here 👉 Discover guides, insights, and resources in Learn 👉 and Knowledge Base 👉 📰 GT Protocol AI Digests 4 new AI Digest issues (No.89–92) are live on Medium, covering AI-native hardware, data privacy, and the evolution of AI agents. Read More 👉 May brought institutional-grade AI strategy management closer to every user.

🪴 GT Protocol Monthly Recap: May 2026 May focused on launching advanced trading infrastructure, introducing AI risk-management tools, and shipping major platform upgrades. 🚀 Hyperliquid Vaults Live Run multiple algorithmic strategies on a single Hyperliquid Vault inside GT App. Enjoy automated execution, auto-rebalancing, and protocol-level security. You can find Vault trading on the Hyperliquid exchange account connection page in the Trade on Vault section. Try it in GT App 👉 🤖 AI Hedge Fund Experiment Live An experimental AI Hedge Fund powered by 5 independent LLM models is live on Hyperliquid. Each model manages $10,000 to test different AI trading personalities and allocation strategies. Discover it now here 👉 📈 Isolated Margin & AI Risk Tools Isolated Margin is live across GT App for precise risk management. Enhanced with AI-powered logic, it assists with dynamic asset monitoring and smarter strategy deployment. Try it in GT App 👉 🔥 Top Strategy Performance Top trader strategies like "lebakien" achieved over +141% profit this month. Users can explore metrics and follow the strategies of top traders directly in the marketplace. Explore Marketplace 👉 🛠 Key Product Updates ⚙️ Strategy Discovery: enhanced demo trading flows and top trader strategy integration. ⚙️ AI Strategy Chat: demoed a flow to create, launch, and test strategies via natural language chat. ⚙️ Advanced Execution: added manual safety orders for granular control over active positions. ⚙️ Testing & Validation: optimized historical data validation for more accurate strategy testing. ⚙️ Knowledge Hub: launched GT Protocol Learn and a new Knowledge Base for streamlined support. ⚙️ Performance: upgraded website structure and improved overall page responsiveness. Find all the latest GT App updates Here 👉 Discover guides, insights, and resources in Learn 👉 and Knowledge Base 👉 📰 GT Protocol AI Digests 4 new AI Digest issues (No.89–92) are live on Medium, covering AI-native hardware, data privacy, and the evolution of AI agents. Read More 👉 May brought institutional-grade AI strategy management closer to every user.

GT Protocol

32,774 次观看 • 2 个月前

／ 🎊Everyone Wins Giveaway🎊 Starting today, 5/9 (Thu) - Event Dungeon is open‼️ ＼ Win from a total of 520,000 $BC and NFTs during this limited-time event! ✅Play the game and earn fantastic rewards. ✅The game is Free to Play. 🎊Additionally, in celebration of the event dungeon, we're hosting a luxurious Giveaway👇 "All eligible participants" will win! Now is the best time to start! Don’t miss this opportunity to begin playing #ECWiz! 🎁Gifts for Everyone All users who meet the following conditions will receive a "Prize Box Grade 3"! ↑ Randomly contains NFTs or in-game items. 1️⃣ Follow Eternal Crypt - Wizardry BC - | ECWiz, RP/Quote RP and Like this post. 2️⃣ Register for WizardryBC and complete the tutorial. ▼App Store ▼Google Play ▼Browser version 3️⃣ Access the form below and respond with the email address you registered in the game. 4️⃣ Reach at least floor 7-1 in the event dungeon. 5/14 (Tue) 2:59 p.m. UTC 🚨Attention Rewards will be granted in the game later only to users who meet all conditions 1️⃣ to 4️⃣. If any of the conditions are not met, you will not be eligible for the reward. Please be aware. 🎁Raffle Gift Campaign In addition to the gift-for-all campaign, a raffle for 10 people will be held to win a Candidate List (Character NFT)! Follow Eternal Crypt - Wizardry BC - | ECWiz, RP or Quote RP, and like this post. #WizardryBC #ECWiz

／ 🎊Everyone Wins Giveaway🎊 Starting today, 5/9 (Thu) - Event Dungeon is open‼️ ＼ Win from a total of 520,000 $BC and NFTs during this limited-time event! ✅Play the game and earn fantastic rewards. ✅The game is Free to Play. 🎊Additionally, in celebration of the event dungeon, we're hosting a luxurious Giveaway👇 "All eligible participants" will win! Now is the best time to start! Don’t miss this opportunity to begin playing #ECWiz! 🎁Gifts for Everyone All users who meet the following conditions will receive a "Prize Box Grade 3"! ↑ Randomly contains NFTs or in-game items. 1️⃣ Follow Eternal Crypt - Wizardry BC - | ECWiz, RP/Quote RP and Like this post. 2️⃣ Register for WizardryBC and complete the tutorial. ▼App Store ▼Google Play ▼Browser version 3️⃣ Access the form below and respond with the email address you registered in the game. 4️⃣ Reach at least floor 7-1 in the event dungeon. 5/14 (Tue) 2:59 p.m. UTC 🚨Attention Rewards will be granted in the game later only to users who meet all conditions 1️⃣ to 4️⃣. If any of the conditions are not met, you will not be eligible for the reward. Please be aware. 🎁Raffle Gift Campaign In addition to the gift-for-all campaign, a raffle for 10 people will be held to win a Candidate List (Character NFT)! Follow Eternal Crypt - Wizardry BC - | ECWiz, RP or Quote RP, and like this post. #WizardryBC #ECWiz

Eternal Crypt - Wizardry BC - | ECWiz

30,393 次观看 • 2 年前