NEW: Video input support 🎥 Analyze videos with a stateless API. Browse all compatible LLMs here: openrouter.ai/models?fmt=car…

Excellent walkthrough of how to build a streaming agent in @nextjs using LangChain. Clear explanation of server-sent events, UI streaming, and memory via thread IDs. If you’re evaluating production agent architectures, this is a strong reference implementation. 👇 Watch the full video here: piped.video/watch?v=piK5WTXA… 🧑‍💻 Clone the repository and give it a go: github.com/christian-bromann…

New chat LangChain! Check it out

Attach Dreambase to Supabase and you get all these gorgeous charts

This guy removed the "nice" filter from ChatGPT and got way better results. I tried it and it works very well.

This guy literally dropped the best mindset shift you’ll ever hear

🚨NEW: Python library for LLM Prompt Management This is what it does:

🏦 AI Bank Statement Analyzer (Made by the LangChain Community) Transform bank statements into queryable financial insights using AI. This system combines YOLO and LangChain's RAG to enable natural language analysis of your personal finances. Check it out here ⚡ github.com/johnsonhk88/AI-Ba…

Este artículo me encantó: “Cómo uso cada feature de Claude Code” Es una inmensidad de funciones! blog.sshh.io/p/how-i-use-eve…

MCP 🤝 Replit

Incredible to see how far Agno's come from being a class that helped me extract actions (from ReAct), run them, and manage state in a db. After running into the same problem for multiple customers, I open-sourced the library and the rest is history. Still OSS, still building.

Tools I use for screenshots, videos, and code snippets 👇 > Code: ray.so (any theme works) > Videos: screen.studio (worth every penny) > Screenshots: shots.so (radiant gradient bg, noise ~55)

Product planning shouldn’t start from a blank page. Your best ideas are already waiting — if you’ve been collecting them along the way. → linear.app/now/continuous-pl…

DeepWiki by @cognition is ridiculously good. Here's the @AgnoAgi overview page, clean and beautifully structured: deepwiki.com/agno-agi/agno/1…

Introducing Company Knowledge for Slack! 🧠 Company Knowledge from @OpenAI uses Slack's new RTS API to give you more relevant, tailored answers. ChatGPT securely draws from your organization’s work in Slack to provide answers unique to your company, all within the context of your team’s conversations. No more generic responses — just insights that understand your business context. 💡 Learn more: sforce.co/4nqFp5u

Yesterday we did a livestream. TL;DR: We have set internal goals of having an automated AI research intern by September of 2026 running on hundreds of thousands of GPUs, and a true automated AI researcher by March of 2028. We may totally fail at this goal, but given the extraordinary potential impacts we think it is in the public interest to be transparent about this. We have a safety strategy that relies on 5 layers: Value alignment, Goal alignment, Reliability, Adversarial robustness, and System safety. Chain-of-thought faithfulness is a tool we are particularly excited about, but it somewhat fragile and requires drawing a boundary and a clear abstraction. On the product side, we are trying to move towards a true platform, where people and companies building on top of our offerings will capture most of the value. Today people can build on our API and apps in ChatGPT; eventually, we want to offer an AI cloud that enables huge businesses. We have currently committed to about 30 gigawatts of compute, with a total cost of ownership over the years of about $1.4 trillion. We are comfortable with this given what we see on the horizon for model capability growth and revenue growth. We would like to do more—we would like to build an AI factory that can make 1 gigawatt per week of new capacity, at a greatly reduced cost relative to today—but that will require more confidence in future models, revenue, and technological/financial innovation. Our new structure is much simpler than our old one. We have a non-profit called OpenAI Foundation that governs a Public Benefit Corporation called OpenAI Group. The foundation initially owns 26% of the PBC, but it can increase with warrants over time if the PBC does super well. The PBC can attract the resources needed to achieve the mission. Our mission, for both our non-profit and PBC, remains the same: to ensure that artificial general intelligence benefits all of humanity. The nonprofit is initially committing $25 billion to health and curing disease, and AI resilience (all of the things that could help society have a successful transition to a post-AGI world, including technical safety but also things like economic impact, cyber security, and much more). The nonprofit now has the ability to actually deploy capital relatively quickly, unlike before. In 2026 we expect that our AI systems may be able to make small new discoveries; in 2028 we could be looking at big ones. This is a really big deal; we think that science, and the institutions that let us widely distribute the fruits of science, are the most important ways that quality of life improves over time.

Prompt-to-MCP

Rather than relying on manual checks or static rules, Sierra’s platform enables you to use AI supervisors and monitors to make agents dependable — correcting them in real time, and continuously evaluating the quality of every conversation sierra.ai/blog/confidence-in…

Nice landing page — elevenlabs.io/studio Very simple, focused on the words + supporting graphics, doesn't try to distract me with shiny things.

🎯 New Release: Smart Tool History Management! Reduce token costs and prevent context overflow! Perfect for research agents and web scrapers that make multiple tool calls per conversation. The new max_tool_calls_from_history parameter keeps your agents focused on recent tool results while your database stores everything. 👉 Getting started is simple: set max_tool_calls_from_history when creating your agent to limit historical tool calls in context. Link to documentation below 👇👇