Image created with Flux Pro v1.1 Ultra. Image prompt: photorealistic still image of a middle-aged man standing behind a woman, woman covering part of her face with her hand, man looking over her shoulder, both illuminated with warm stadium jumbotron lighting, natural skin tones, subtle lens flare, shallow depth of field, exact color temperature of a live event projection, both wearing white t-shirts with the Anthropic logo printed clearly across the chest, cinematic realism –no text, captions, watermarks
Building and evaluating alignment auditing agents https://alignment.anthropic.com/2025/automated-auditing/
Claude Code from @AnthropicAI is amazing! I built a Mac app with the Claude Code SDK if you want to try it out. It’s free and open source. The best part is that it has Xcode integration, you can use cmd+i to send code selections to the context and more! https://x.com/jamesrochabrun/status/1949889166680228303
Claude Code is All You Need When I first joined Anthropic I was surprised to learn that lots of the team used Claude Code as a general agent, not just for code. I’ve since become a convert! I use Claude Code to help me with almost all the work I do now, here’s how: https://x.com/trq212/status/1944877527044120655
Claude Code is the best coding agent AND general agent in the world. Let’s talk about: – Setting up Claude Code – Using it as a general agent (Research + Content) – Claude Code + @obsdmd – Building and deploying web apps @vercel @github – Database + Auth @Firebase https://x.com/rileybrown_ai/status/1948846549913796650
Pro Tip: Claude Code is now an online shopper Took our 340 million walmart products. Built an AI ready MCP server integration and dropped it directly into Claude Code. Finding deals on the internet, shopping, and sourcing is about to get a major upgrade. What are your https://x.com/NickSpisak_/status/1944253705391366591
After DeepSeek R1, there’s new Claude 4 level model from China that outperforms DeepSeek v3, Qwen and OpenAI GPT-4.1 Meet Kimi k2 – 1 trillion parameter model purpose-built for agentic workflows with native MCP integration. 100% Opensource and FREE to try. Let that sink in. https://x.com/Saboo_Shubham_/status/1943694224584818808
New Anthropic research: Building and evaluating alignment auditing agents. We developed three AI agents to autonomously complete alignment auditing tasks. In testing, our agents successfully uncovered hidden goals, built safety evaluations, and surfaced concerning behaviors. https://x.com/AnthropicAI/status/1948433493102403876
Claude Code Templates now has a web interface for browsing and contributing templates 🙌 What it does: Install templates for different languages/frameworks to get started with Claude Code faster. How to use: – Go to https://x.com/dani_avila7/status/1946565851408400814
RT @AnthropicAI: New Anthropic research: Persona vectors. Language models sometimes go haywire and slip into weird and unsettling personas…”” / X https://x.com/EthanJPerez/status/1951364045283741940
setting up Claude Code is the hardest part for non-technical users. get going quickly with these prompts https://x.com/boringmarketer/status/1947274520705851741
Claude code just made this whole video using remotion One shot wtf https://x.com/jasonzhou1993/status/1948355284591956447
Scoop: Anthropic revoked OpenAI’s API access to its models on Tuesday, multiple sources familiar with the matter tell WIRED. OpenAI was informed that its access was cut off due to violating the terms of service. https://x.com/kyliebytes/status/1951399513291166132
And @Microsoft!”” / X https://x.com/Yoshua_Bengio/status/1951270687957553235
EU AI Act: General-Purpose AI Code of Practice · Final Version
https://code-of-practice.ai/?section=safety-security
Yoshua Bengio on X: “I’ve been thrilled to see the support for the Safety & Security Chapter of the Code of Practice. Most frontier AI companies have now signed on to it: @AnthropicAI, @Google, @MistralAI, @OpenAI, @xAI Why this is important: 🧵 1/6″ / X
https://x.com/Yoshua_Bengio/status/1951263044056588677
👀 Did you catch our webinar with @nocodebackend on MCP? We explained how to build an MCP client using WeWeb AI and set up an MCP server in Xano to create a conversational CRM just like ChatGPT. We’re thinking about doing a Part 2, diving deeper into: ✅ Multi-agent workflows https://x.com/weweb_io/status/1945423231680458937
🔟 FastAPI MCP server A zero-config tool for automatically convert FastAPI endpoints as MCP tools and use them with Clause, Cursor or any MCP client 100% open-source. https://x.com/akshay_pachaar/status/1943648808594010249
🤖 We built a customer feedback router with built-in MCP support https://x.com/dify_ai/status/1944813314971983915
🧲 Meet Magnet — the AI workspace for agentic coding. Build software with Claude Code, Cursor, Codex & co. → Write a ticket → Magnet assembles context → Fires to Claude Code, Deep Research, and other agent sessions in parallel Git worktree sandboxes → PRs appear → Use https://x.com/NicolaeRusan/status/1946339551334822195
After a 2-year hiatus from writing blogs, I finally wrote one again. And it is about MCP! I learned from the best @TejasKumar_, @kentcdodds, & @JamesMontemagno 👏🏽👏🏽. Thanks to the content you all made! The link to the article with the Github repo is here https://x.com/DevlinDuldulao/status/1943602128267653607
Been loyal to @cursor_ai for months, but decided to test @AnthropicAI Claude Code today. Mind. Blown. 🤯 We built a basic @calai_app app in just 30 minutes. (Really! no marketing gimmick.) The accuracy and code quality? Next level. 🔥 I can say this isn’t just hype, it’s a https://x.com/daxesh_iroid/status/1949461634205749269
Built a real-time whiteboard app where an LLM can draw with you. VS Code + MCP made it dead simple. Just one custom tool, no model code, and real-time updates handled by Azure PubSub. 🔗 https://x.com/WirelessLife/status/1944838306812060082
Claude Code can be impossible to work with. When trying to work regularly on coding projects (or even when recording the Claude Code course as I’m doing now) – we keep getting 529 Error which means that the Claude Sonnet 4 API is overloaded with requests. This also means that it https://x.com/yuvalav/status/1947195213912613011
Claude Code has a serious competitor. Warp lets you interact with AI Agents directly from your terminal. I used it to download a YouTube video, clip it, and caption it with Whispr AI. All of this in less than 2 mins. https://x.com/Saboo_Shubham_/status/1907258559521599773
Claude Code pro tip: The GitHub action now works with your Max plan! 🔥 Run: /install-github-app And you have an instant background agent in your GitHub issues and PRs https://x.com/iannuttall/status/1943417178642100260
Claude Code sub-agents is probably the easiest way to build complex, custom agentic systems. Not just for code, but for anything you can imagine. Watch me build a multi-agent deep research system with Claude Code subagents. Chain subagents with /commands for reliability. https://x.com/omarsar0/status/1949204315350216789
Claude Code that works with any LLM. OpenHands CLI brings AI agents to your Terminal with zero vendor lock-in and zero subscriptions. Works with Claude Sonnet 4 or local AI models like Llama, Qwen, etc. 100% Opensource. https://x.com/Saboo_Shubham_/status/1938615423299403988
Claude Code with full visibility into what your agents are doing 👀 npx claude-code-templates@latest –chats Opens localhost:3333 with: • Real-time conversations • Token usage tracking • Tool call details • Session analytics Runs locally = full privacy 🔒 Repo: https://x.com/dani_avila7/status/1948389203408003189
Claude Code’s auto-compact ruins your context. I built a fix. Keep your last 15 messages. Delete the rest. No awful summaries. npx claude-prune Watch me use it 👇 https://x.com/DannyAziz97/status/1945958948227461329
First demo of my local voice transcription app! The video shows refactoring a feature with Amazon’s VS Code fork Kiro (failed) and Claude Code (worked). App Features: – User-friendly UI – 100% local processing – Global hotkey – Auto-paste into text fields – Free at launch https://x.com/AidfulAI/status/1945837275369394412
framework for building MCP servers with Python https://x.com/tom_doerr/status/1944285710523027580
GitHub Copilot coding agent just got a major upgrade. ✨ What’s new: • It tests its own UI changes with Playwright and adds screenshots to PRs. • It can connect to more context and tools with remote MCP support. • You can trigger and track tasks from a new dashboard. • It https://x.com/github/status/1944826853048438832
Here’s my 1hr tutorial on how to use Claude Code for notes & research. 10x your notes with: – core agentic flows – custom commands – automated tags/links – subagents – cloud usage – stt The goal is to “agent-pill” you on the future of work. Watch for 10 tips + demos in 61min. https://x.com/mckaywrigley/status/1943034127462339060
How might AI integration and model context protocol (MCP) servers change BI tools? We’ve written a short article with thoughts and speculations on the matter. Link below. https://x.com/kurtbuhler/status/1944668855692923186
I built 7 custom subagents for Claude Code to help me ship faster! 1. code-refactorer 2. prd-writer 3. project-task-planner 4. vibe-coding-coach 5. security-auditor 6. frontend-designer 7. content-writer (Try them yourself from the link below) https://x.com/iannuttall/status/1948702664348631446
I used Claude Code to vibe code an app that helps me make friends with nearby crows 🐦⬛ https://x.com/GregFeingold/status/1945531985146810767
I’m going to finally OSS the final version of this MCP Memory server I’ve been using as my daily driver – haven’t been talking about it as much lately because I’ve been busy using it! https://x.com/Aaronontheweb/status/1945113137012785273
Introducing the Scira MCP Suite 🚀🚀 🚨 Today I am launching the official MCP server for the Scira API and reintroducing Scira MCP Chat! Scira MCP Server An open source MCP server built on top of the Scira API using @xmcp_dev and hosted on @vercel! → web search – AI powered https://x.com/zaidmukaddam/status/1945513686480855535
Introducing zMCP, the zero-dependency Java 21 Model Context Protocol (MCP) server. I presented the implementation at the ‘LLM/GenAI Patterns, Architectures and Use Cases’ https://x.com/AdamBien/status/1945064056139702629
Introducing: Notion MCP Server (hosted, v2) We worked with the @cursor_ai team to rebuild our MCP from the ground up: – 1-click OAuth install for Claude, ChatGPT, and Cursor… – inventing a Notion-flavored Markdown that combines the power of Notion blocks with the compactness https://x.com/ivanhzhao/status/1945167473617293429
Just booked a call with the CEO of Microsoft, for free Not through connections. Not through his assistant. Through my terminal. Used MCP Shell → Connected @composiohq + @useapolloio → Bypassed every gatekeeper between me and @satyanadella Just going to book calls with CEOs, https://x.com/prathitjoshi_/status/1944811631453544879
Just built a typing game on Claude Code using k2 (Kimi’s latest model), it’s cracked AF https://x.com/Khazzz1c/status/1943625882913906869
Just dropped some updates to the Claude Code Analytics Dashboard 👇 Now you get way more insight into how you’re actually using Claude Code – from session limits to cache efficiency. Setup simple running: npx claude-code-templates@latest That’s it. One command and you’re https://x.com/dani_avila7/status/1945268457680883775
Make your own MCP server to chat with data in a Power BI semantic model, in any workspace. Full instructions, sample files included; try it out (Link below) https://x.com/kurtbuhler/status/1945393937549578461
Model Context Protocol (MCP) lets AI agents connect to your tools, but without access control, one prompt can do too much. With @pomerium_io, we set fine-grained policies on servers, all the way down to the tool level. No cooking the books today with zero trust. https://x.com/nickytonline/status/1943792380651655613
My attempt at developing a Burst-optimized, zero-GC allocation C# half-edge structure library for Unity, with help from a coding agent (Claude Code). Wrote a brief wrap-up of the experiment: https://x.com/_kzr/status/1947255501269487715
My new sign to call it a day – keep pushing with claude code until it locks you out. A beautiful, world class voice agent platform built with @livekit is on the way https://x.com/28gautam97/status/1949875839098593437
Neat way to use Claude code as a general agent Setup agent rules for your entire file system and folders. Can see this becoming a big way to use your computer I hadn’t really considered working with multiple directories outside a codebase like this https://x.com/NickADobos/status/1945362463928803409
new @every CLI for doing compounding engineering with Claude Code https://x.com/danshipper/status/1948047598075408877
Often AI Agents work as teams, requiring interoperability between them. The open source Strands Agents SDK makes it easy to connect agents together using the Model Context Protocol (MCP). Learn how in part 3 of our blog series: https://x.com/AWSOpen/status/1943708623097508062
Projectile impact effect in three.js, built with assitance from Claude Code https://x.com/evanqjones/status/1944560069208858812
RT @_avichawla: An MCP server that makes anyone a database engineer (open-source)! @MongoDB just released an MCP Server that lets AI tools…”” / X https://x.com/_avichawla/status/1951010303812014134
RT @CerebrasSystems: Cerebras Code: 20x faster than Claude, 1x the price Today we are launching two monthly coding plans: ➡️Cerebras Code…”” / X https://x.com/jeremyphoward/status/1951370781755318310
RT @reach_vb: NEW: GLM-4.5 & GLM-4.5-Air from @Zai_org – competitive w/ claude 4 opus and beats Gemini 2.5 Pro, MIT license🔥 > GLM-4.5: 35…”” / X https://x.com/Zai_org/status/1949970927006949430
RT @UnslothAI: You can now run the world’s most powerful Western open models locally! The hybrid reasoning 671B model matches o3 & Claude-…”” / X https://x.com/_lewtun/status/1951087047332241522
Ship your API to every MCP client in minutes 🚢 Upload your OpenAPI spec to @StainlessAPI → Generate an MCP Server → Your users can access your API in @claude_code, @cursor_ai, and VS Code Watch me use the @replicate MCP Server to create a logo for my upcoming AI Podcast https://x.com/adamanzzz/status/1943286834999513416
The only MCP server you’ll ever need! MindsDB lets you query data from 200+ sources, like Slack, Gmail, social platforms, and more, in both SQL and natural language. A federated query engine that comes with a built-in MCP server. 100% open-source with 33k+ stars! https://x.com/_avichawla/status/1944283926622875816
the whop’s first no-code install MCP collection is about to break the internet… while developers are wrestling with terminal commands and complex installations for hours i built something that changes everything 1 URL paste = instant access to premium MCP tools – no https://x.com/paoloanzn/status/1945514126178226179
Tip: You can run multiple code agents in parallel. Works well with Gemini CLI, Claude Code + git-worktree. https://x.com/addyosmani/status/1946676964804399125
Unlocking extensibility with Model Context Protocol (MCP) 🔗 You can now add MCP servers to your Firebase Studio workspace, extending and personalizing your workflows with Gemini. https://x.com/Firebase/status/1943295273880437168
Unreal combo to make videos using your own app @Remotion + Claude Code Needed demo videos for FunnelSurfing Found this workflow Built one in under an hour https://x.com/DrewAutomates/status/1948731068904825130
Vibe coded a simple PHP app using Claude code. Path traversal is prevented via basename functions. Can you still exploit it? A shell is waiting for you at https://x.com/0xacb/status/1945040109906149402
Vibe coded in 10 minute a small video carrousel creation tool with Claude code and remotion. This is just incredible how things are moving fast. Now, you have something in your mind and you just create it on the fly. @AnthropicAI (inspired by @iannuttall ) https://x.com/pierre_vannier/status/1949814757386605055
we’re living in the GREATEST time in HISTORY to turn ideas into reality claude code subagents allows you to organize AI agents like a startup team each one living in its own markdown file with specific instructions, personality traits, and expertise areas, from https://x.com/gregisenberg/status/1949836925952508324
We’re rolling out new weekly rate limits for Claude Pro and Max in late August. We estimate they’ll apply to less than 5% of subscribers based on current usage. https://x.com/AnthropicAI/status/1949898502688903593
you can build a lot in 24h with claude code. here are the hacks from the @every team (many of whom are non-technical): https://x.com/danshipper/status/1948408190523125801
you can just use Claude Code with a simple structure and run it to generate a product strategy – folder with context – folder with steps /init to set up https://x.com/nurijanian/status/1945499679594262912
@ns123abc Performance improvement noted when using @AgentOpsAI MCP in @arcprize ARC-AGI-3 General Reasoning agent. When the agent is able to see its past actions and reasoning, it’s able to perform better since it avoids repeating the same set of events. Prompt engineering must be good to”” / X https://x.com/pratty_agi/status/1948463952016662903
🚨Using Claude Code with Kimi K2, but suffering from slow speeds? The @GroqInc team have Kimi K2 being served at lightning speed ⚡ You can actually use the Groq version for Claude Code to get the best of both worlds! Speed comparison & step by step instructions below 👇 https://x.com/chongdashu/status/1945634662560231570
Tried out Kimi 2 on @GroqInc with OpenCode by @SST_dev and I was pretty impressed. – Speed-wise it was very fast. – Quality of output was on par with Claude Code (spooky theme from Claude was actually not usable) I didn’t include the Claude test in the video. 🙁 https://x.com/th3mus1cman/status/1948006511076135322
Join @walden_yan and the @AnthropicAI team for a deep dive and Q&A on building async agents. Sign up for Thursday’s webinar below. https://x.com/cognition/status/1950283415951200601
In the past I’ve sometimes recommended Claude for kids / normals, on the ground that I’d guessed Claude less likely to be predatory. Alas, this looks like Claude doing the crazymaking. Any known cases yet traceable to Gemini?”” / X https://x.com/ESYudkowsky/status/1948402233659306038
Polymarket Mean Reversion Trading Bot with Claude Code part 1 https://x.com/MoonDevOnYT/status/1948911147500937706
Instructions to Claude Code for using Gemini to help solve problems https://x.com/kylebrussell/status/1948417263268225099
Full video of me using @FAL + Veo3 + Claude Code to programmatically create YouTube intros. Source code, full prompt below. I also talk through some common pitfalls you might encounter doing something like this (i.e rendering text). https://x.com/htormey/status/1949864298718847153
📹What are Deep Agents? (YouTube video) Recorded a quick 10 minute video on what “”Deep Agents”” are. References Claude Code, Manus, and Deep Research Deep Agents = Planning Tool + File System + Sub Agents + Detailed System Prompt Video: https://x.com/hwchase17/status/1950989844936794511
Microsoft Introduced AI Integrations for SQL Server – using MCP Servers with your SQL Server databases and servers – from Brent Ozar https://x.com/ErikEJ/status/1943191047342883269
spinning up claude code agents from my phone using the @terragonlabs cobot @cobotco is almost ready https://x.com/jsngr/status/1948425445956816976
I’m now using Qwen3-Coder in Claude Code. Works with any model actually, but this is surely the best one currently. There are a bunch of proxies on GitHub that make this possible, but none worked well enough for me, so I implemented this myself using LiteLLM. Guide in comments: https://x.com/WolframRvnwlf/status/1948046368213176624
Kimi K2 – On-par with Claude 4, but 80% cheaper!! I connected Kimi K2 to Claude Code to get a sense of real performance (Kimi Code!) Overall findings: 1. Exceptional coding capability 2. Cost only 20% of Claude 4 (Huge!) 2. Only downside is API is a bit slow 🧵 Below is some https://x.com/jasonzhou1993/status/1944320164889284947
Qwen3 Coder has a 5.32% diff edit failure rate in Cline, based on real-world data. It’s right alongside Claude Sonnet 4 and Kimi K2 as an excellent model in performing diff edits. Not bad for an open-source model at $0.30/$1.20 per million input/output tokens 👀 https://x.com/cline/status/1949973297455599998
RT @_avichawla: You can now deploy any ML model, RAG, or Agent as an MCP server. And it takes just 10 lines of code. Here’s a step-by-ste…”” / X https://x.com/_avichawla/status/1950282234893656101
Following @trq212 with the idea of Claude Code for everything. Built a poem to video workflow using /commands and @replicate MCP. You give CC a poem & it makes scenes, generates the images, TTS, music & puts it together with @Remotion. (I know, not perfect, give it a few months) https://x.com/MikeWigmore/status/1948015476870635591
RT @AnthropicAI: We’re running another round of the Anthropic Fellows program. If you’re an engineer or researcher with a strong coding o…”” / X https://x.com/EthanJPerez/status/1950278824102678586
