Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Cursor, Windsurf … all cool. But @AugmentCode just dropped `Augment Agent` 200K context. Persistent memory. Deep tool integrations. ... and it just hit #1 on SWE-bench Verified (65.4% on real tasks). It’s kind of a big deal. Let me show you 🧵 ↓

DataChaz's profile picture

Charly Wargnier

174,783 subscribers

63,421 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

20 Yorum

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

If you haven’t heard of SWE-bench, it’s the gold standard for testing AI agents on real @github issues. Agents must read codebases, reason through tasks, fix bugs unsupervised. Augment’s Agent hit 65.4%, *the* best open-source score to date! Results:

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

I use @cursor_ai a lot, so I honestly wasn’t expecting much from @augmentcode’s Agent. But wow - it plans, edits across files, runs tests, opens PRs - all from a single prompt, inside your IDE. Tried it on a scene data structure w/ confidence scores - nailed it on the first go!

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

.@augmentcode’s Agent also has next-level visual debugging: 1️⃣ Drag in a screenshot 2️⃣ Agent spots the UI issue (CSS, layout, logic) 3️⃣ Suggests a fix 4️⃣ Runs only the relevant tests Pretty ace!

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

🧩 It has persistent memory: - it can learn your coding style - remembers previous refactors - adapts to your infra and conventions It gets smarter the more you use it, no need to start from scratch each time.

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

🧰 Integrated Dev Workflows You can use @augmentcode’s Agent to go from ticket → code → PR without switching tools! e.g.: – @GitHub: branch, commit, PR – @Linear: issue detection + resolution – @Notion, @JIRA, @Confluence: context → implementation Pretty rad.

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

MCP is 🔥 and becoming a must-have in AI tooling. @augmentcode’s Agent supports it natively. – @supabase, @figma, @vercel, @Cloudflare, @getsentry – plug in APIs, SQL, CLI tools via settings.json You can even add your own tools to the agent’s context. →

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

Right now, you can try @augmentcode’s Augment Agent with unlimited agent calls. The folks at AugmentCode told me they’ll switch to usage-based pricing later - but for now, there’s absolutely no cap! Try it here →

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

That’s a wrap! If you found this thread useful, a quick RT goes a long way, especially for small teams like @augmentcode taking on the giants! 🦾 Follow me → @datachaz for takes on AI, LLMs, and agents. No fluff I promise.

Jeremy Wickersheimer profil fotoğrafı
Jeremy Wickersheimer1 yıl önce

@augmentcode The one thing I thought was missing, they added it. Very cool

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

@augmentcode Glad to hear, Jeremy! 🤗

Rama Jha (🏗️📝🎓) profil fotoğrafı
Rama Jha (🏗️📝🎓)1 yıl önce

@augmentcode 200K context AND persistent memory?! 👀 That's next level!

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

@augmentcode Man... I'm switching to it from Cursor! 🔥

xavier lois profil fotoğrafı
xavier lois1 yıl önce

@augmentcode Let me know when one of these tool finally manages to implement a proper software architecture ... and is able to stick to it!

Charly Wargnier profil fotoğrafı
Charly Wargnier1 yıl önce

@augmentcode what do you mean by "and is able to stick to it"?

BitFuturist profil fotoğrafı
BitFuturist1 yıl önce

@augmentcode AugmentCode is the next level 👍🏾

Mike H (eboss/acc) profil fotoğrafı
Mike H (eboss/acc)1 yıl önce

@augmentcode Love @augmentcode - def a tool that deserves more love

GamePrompts profil fotoğrafı
GamePrompts1 yıl önce

@augmentcode ohh this this looks nice, good little qol with the drag and capture thing

VibeCode profil fotoğrafı
VibeCode1 yıl önce

@augmentcode interesting

Mr Mastrianni (🚀,🔴) profil fotoğrafı
Mr Mastrianni (🚀,🔴)1 yıl önce

@augmentcode I have a hard time logging in

Alexander Myasoedov profil fotoğrafı
Alexander Myasoedov1 yıl önce

INTRODUCING: Agentic Security - LLM Security Scanner! 🔍 🔑 Features: Scans for prompt injections, jailbreaking & more. Provides detailed reports & options to customize attack rules. 🔗access the GitHub Link ↓

Benzer Videolar

A new frontier AI model just dropped on OpenRouter and it’s free. Pony Alpha delivers 200k context, visible reasoning, adjustable thinking depth, and agent-ready tool calling that rivals (and beats) Opus 4.5 in benchmarks. This one’s serious.
9:08

A new frontier AI model just dropped on OpenRouter and it’s free. Pony Alpha delivers 200k context, visible reasoning, adjustable thinking depth, and agent-ready tool calling that rivals (and beats) Opus 4.5 in benchmarks. This one’s serious.

Mervin Praison

23,400 görüntüleme • 5 ay önce

Love OpenClaw but don't trust the security? Now you can have your own private agent running in Pokee secure sandbox, with 1000s of secure tool integrations. Vibe code on a GitHub repo, automate sales, deep research—all from 1 agent. Open to first 100 ppl!
1:30

Love OpenClaw but don't trust the security? Now you can have your own private agent running in Pokee secure sandbox, with 1000s of secure tool integrations. Vibe code on a GitHub repo, automate sales, deep research—all from 1 agent. Open to first 100 ppl!

Pokee AI

799,117 görüntüleme • 4 ay önce

Day 1/6 of CodeGuide 2.0 🧡 Introducing Codie - AI Agent that can help you Code on any AI Coding tool Just Screen Share and Ask for Realtime help: - Setting up Project Files - Debugging Errors - Deployment etc In this Demo I used CodeGuide x StackBlitz to show you how it works You can also use Codie with: - Cursor AI - Windsurf - Lovable - Replit - v0 Enjoy.
8:09

Day 1/6 of CodeGuide 2.0 🧡 Introducing Codie - AI Agent that can help you Code on any AI Coding tool Just Screen Share and Ask for Realtime help: - Setting up Project Files - Debugging Errors - Deployment etc In this Demo I used CodeGuide x StackBlitz to show you how it works You can also use Codie with: - Cursor AI - Windsurf - Lovable - Replit - v0 Enjoy.

CJ Zafir

23,139 görüntüleme • 1 yıl önce

We’re excited to launch OpenMemory MCP, a private memory for MCP-compatible clients powered by mem0 Today, most AI assistants and dev tools operate without memory. You plan your roadmap in Claude, implement tasks in Cursor, but none of them know what the other did. Each tool operates in isolation, and your context disappears as soon as the session ends. OpenMemory MCP solves this. Built on the open Model Context Protocol (MCP), OpenMemory MCP runs 100% locally and provides a persistent, portable memory layer for all your AI tools. It enables agents and assistants to read from and write to a shared memory, securely and privately. Key capabilities: ✅Works across MCP clients like Cursor, Claude Desktop, Windsurf, Cline and more ✅Provides standardized memory operations (add_memories, search_memory, list_memories, delete_all_memories) ✅Stores data on your machine, fully private ✅Offers a centralized dashboard for visibility and control ✅Simple Docker-based setup with no vendor lock-in If you're building on MCP, OpenMemory MCP is the easiest way to add persistent, private memory to your clients with zero cloud dependencies and full local control. We’ve put together a short demo to show how it works Check it out in the links below 👇
2:24

We’re excited to launch OpenMemory MCP, a private memory for MCP-compatible clients powered by mem0 Today, most AI assistants and dev tools operate without memory. You plan your roadmap in Claude, implement tasks in Cursor, but none of them know what the other did. Each tool operates in isolation, and your context disappears as soon as the session ends. OpenMemory MCP solves this. Built on the open Model Context Protocol (MCP), OpenMemory MCP runs 100% locally and provides a persistent, portable memory layer for all your AI tools. It enables agents and assistants to read from and write to a shared memory, securely and privately. Key capabilities: ✅Works across MCP clients like Cursor, Claude Desktop, Windsurf, Cline and more ✅Provides standardized memory operations (add_memories, search_memory, list_memories, delete_all_memories) ✅Stores data on your machine, fully private ✅Offers a centralized dashboard for visibility and control ✅Simple Docker-based setup with no vendor lock-in If you're building on MCP, OpenMemory MCP is the easiest way to add persistent, private memory to your clients with zero cloud dependencies and full local control. We’ve put together a short demo to show how it works Check it out in the links below 👇

Taranjeet

471,767 görüntüleme • 1 yıl önce

I just found a web agent framework built specifically for LLMs. It turns any site into clean, agent-ready text. Any LLM can now act on the web. It’s called Notte, and it changes everything. Let me show you how:
0:39

I just found a web agent framework built specifically for LLMs. It turns any site into clean, agent-ready text. Any LLM can now act on the web. It’s called Notte, and it changes everything. Let me show you how:

Markandey Sharma

52,026 görüntüleme • 1 yıl önce

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:
1:28

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

Swami Sivasubramanian

28,946 görüntüleme • 1 yıl önce

I had Darren Waller down to the FFCA and he let me hear his new song ‘Top Play’ and guess what… I LOVED IT Lucky for all of you, ‘Top Play’ just dropped TODAY and it’s live on all platforms. Go listen!
2:17

I had Darren Waller down to the FFCA and he let me hear his new song ‘Top Play’ and guess what… I LOVED IT Lucky for all of you, ‘Top Play’ just dropped TODAY and it’s live on all platforms. Go listen!

Jon Gruden

1,001,007 görüntüleme • 1 yıl önce

🚨🇬🇧 Keir Starmer just dropped this clip depicting illegal migrants being detained as part of the deal with France Don’t believe it. Nothing changes. It’s all a show - you are literally watching a movie, whilst the destruction of Europe continues in real time.
0:21

🚨🇬🇧 Keir Starmer just dropped this clip depicting illegal migrants being detained as part of the deal with France Don’t believe it. Nothing changes. It’s all a show - you are literally watching a movie, whilst the destruction of Europe continues in real time.

Concerned Citizen

11,079 görüntüleme • 11 ay önce

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!
1:37

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

159,737 görüntüleme • 4 ay önce

A lot of people think quantum computing is just a made up thing, but Sharbel just schooled us on what it really is. It's the real deal, and it's gonna shake things up big time
0:43

A lot of people think quantum computing is just a made up thing, but Sharbel just schooled us on what it really is. It's the real deal, and it's gonna shake things up big time

Harly™️

10,635 görüntüleme • 5 ay önce

China just dropped a free AI super agent that can build software for you. It’s called DeerFlow 2.0. And it’s exploding on GitHub right now. This thing doesn’t just chat. You give it a goal. - It researches the problem. - Writes the code. - Creates files. - Launches sub-agents. Then delivers a finished result. Basically… an AI dev team in one tool.
0:29

China just dropped a free AI super agent that can build software for you. It’s called DeerFlow 2.0. And it’s exploding on GitHub right now. This thing doesn’t just chat. You give it a goal. - It researches the problem. - Writes the code. - Creates files. - Launches sub-agents. Then delivers a finished result. Basically… an AI dev team in one tool.

Julian Goldie SEO

231,446 görüntüleme • 4 ay önce

cursor design mode + remotion is actually insane everything in remotion is code, so you can annotate changes directly on the video and cursor just updates it. having a lot of fun with this here's 15 minutes of me improving the agent swarm video
3:04

cursor design mode + remotion is actually insane everything in remotion is code, so you can annotate changes directly on the video and cursor just updates it. having a lot of fun with this here's 15 minutes of me improving the agent swarm video

eric zakariasson

155,481 görüntüleme • 2 ay önce

Forget Roo, Cline, Windsurf, Cursor. Augment Code keeps raising the bar. Tried it on a fun project I hadn’t touched in months. Instead of random refactors, it rebuilt the architecture coherently, understanding the whole codebase → structure, dependencies + Git history. And where tools like Cursor often struggle with large repos or lose track of cross-file relationships... Augment mapped everything. Instantly 🤯 Once the full context is loaded, you can move ridiculously fast: → Restructure / rename components across repos → Swap between GPT-5, Claude Sonnet 4 / 4.5, and Claude Haiku via their Model Picker → Offload builds, tests, deploys to Remote Agents A few extras I really loved: → I could stay in VS Code, JetBrains IDEs... even Vim, which is v. cool! → If you prefer the terminal, the Auggie CLI now gives you the same experience headless. → It also handled a bunch of massive repos I threw at it smoothly, while Cursor struggled to even index them! → It always previews planned refactors before running them 🫶 ____ You can give Augment Code a try here → Big thx to the Augment Code team for partnering with me on this post, I learned a ton along the way! 🙏
0:31

Forget Roo, Cline, Windsurf, Cursor. Augment Code keeps raising the bar. Tried it on a fun project I hadn’t touched in months. Instead of random refactors, it rebuilt the architecture coherently, understanding the whole codebase → structure, dependencies + Git history. And where tools like Cursor often struggle with large repos or lose track of cross-file relationships... Augment mapped everything. Instantly 🤯 Once the full context is loaded, you can move ridiculously fast: → Restructure / rename components across repos → Swap between GPT-5, Claude Sonnet 4 / 4.5, and Claude Haiku via their Model Picker → Offload builds, tests, deploys to Remote Agents A few extras I really loved: → I could stay in VS Code, JetBrains IDEs... even Vim, which is v. cool! → If you prefer the terminal, the Auggie CLI now gives you the same experience headless. → It also handled a bunch of massive repos I threw at it smoothly, while Cursor struggled to even index them! → It always previews planned refactors before running them 🫶 ____ You can give Augment Code a try here → Big thx to the Augment Code team for partnering with me on this post, I learned a ton along the way! 🙏

Charly Wargnier

31,025 görüntüleme • 8 ay önce

Back on 2024 media day, I asked Terrence Shannon Jr about his GTA Code tattoo for unlimited ammo. “Umm, we were in Spain, one of our staff at Illinois were just joking around… that’s kind of how it came about, but then I just looked at it as kind of a cheat code… I just looked up on GTA unlimited ammo and I just got it as a tattoo, I thought it was cool, it’s something me and Quay came up with together and we just ride with it”
0:50

Back on 2024 media day, I asked Terrence Shannon Jr about his GTA Code tattoo for unlimited ammo. “Umm, we were in Spain, one of our staff at Illinois were just joking around… that’s kind of how it came about, but then I just looked at it as kind of a cheat code… I just looked up on GTA unlimited ammo and I just got it as a tattoo, I thought it was cool, it’s something me and Quay came up with together and we just ride with it”

Andrew Dukowitz

90,800 görüntüleme • 2 ay önce

𝗞𝗶𝗺𝗶 𝗞𝟮.𝟲 𝗶𝘀 𝗖𝗵𝗶𝗻𝗮'𝘀 𝗻𝗲𝘄 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲 𝗮𝗻𝘀𝘄𝗲𝗿 𝘁𝗼 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲. It has 1 trillion parameters but only uses 32 billion at a time. Context window holds 256,000 tokens. It scored 85% on Live Code Bench. Claude hit 64%. It plugs into OpenClaw, Cursor, and Cline with no restrictions. Kimi Claw deploys in the cloud in 2 minutes. It's way cheaper to run than Claude day to day. Save this. Your coding stack just got a real rival.
8:31

𝗞𝗶𝗺𝗶 𝗞𝟮.𝟲 𝗶𝘀 𝗖𝗵𝗶𝗻𝗮'𝘀 𝗻𝗲𝘄 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲 𝗮𝗻𝘀𝘄𝗲𝗿 𝘁𝗼 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲. It has 1 trillion parameters but only uses 32 billion at a time. Context window holds 256,000 tokens. It scored 85% on Live Code Bench. Claude hit 64%. It plugs into OpenClaw, Cursor, and Cline with no restrictions. Kimi Claw deploys in the cloud in 2 minutes. It's way cheaper to run than Claude day to day. Save this. Your coding stack just got a real rival.

Julian Goldie SEO

102,184 görüntüleme • 3 ay önce

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:
0:46

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

226,054 görüntüleme • 4 ay önce