What better way to wrap up the new year other than bringing the latest OpenAI GPT-5.2 models into Langflow and having some fun along the way. David Jones-Gilardi tests out GPT-5.2's ability to one-shot a working holiday themed app and the results are pretty cheery. 🌲 ❄️ 💻 https://lnkd.in/eF6dEhDY
Langflow
Software Development
Uberlândia, Minas Gerais 13,036 followers
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model,
About us
Langflow is a new, visual way to build, iterate and deploy AI apps.
- Website
-
https://www.langflow.org/
External link for Langflow
- Industry
- Software Development
- Company size
- 11-50 employees
- Headquarters
- Uberlândia, Minas Gerais
- Type
- Self-Owned
- Founded
- 2020
- Specialties
- AI, Generative AI, GenAI, RAG, and Machine Learning
Locations
-
Primary
Get directions
Uberlândia, Minas Gerais, BR
Employees at Langflow
Updates
-
Did you know you can use OpenAI's latest #GPT-5.2 models in Langflow? It's super easy. We'll show you how along with demonstrating the new Smart Router component in Langflow 1.7. Click the link, watch the vid. 😀 💻 https://lnkd.in/eU3xA7bW
OpenAI's GPT-5.2 in Langflow
https://www.youtube.com/
-
Langflow 1.7 is here, just in time for hacking over the holidays! We've got a ton of goodies for developers to unwrap 🎁 Here are the highlights 👇 🌐 Streamable HTTP for MCP (clients + servers) Langflow now supports Streamable HTTP across both MCP clients and servers. That means you can connect to any MCP server regardless of transport—and expose your Langflow projects the same way. 🤖 New agent components: ALTK & CUGA • ALTK improves agent reliability with tool validation and smart JSON post-processing (no more bloated context windows). • CUGA (from IBM Research) enables agents that can plan, break down complex tasks, write code, browse the web, and act across tools. These are serious upgrades for real-world agent workflows. 🔐 Authenticated webhooks Webhook triggers now support API key authentication—making it much safer to run Langflow flows in production. ☁️ AWS S3 file storage Uploaded files can now be stored in S3 instead of local disk, making Langflow a much better fit for cloud and team deployments. 🧩 A wave of new components LLM Selector, Smart Router, CometAPI (500+ models), AWS Bedrock Converse, flow control, mock data, and more. 👉 Check out the release, star the repo, join the community—and start building. Can’t wait to see what people ship with this 🚀 https://lnkd.in/gQDa7YkK
-
The Flow is back with a holiday episode, and we’re diving straight into the chaos and promise of MCP. Join David Jones-Gilardi and Mihai Criveti, Distinguished Engineer for Agentic AI at IBM and CTO of ContextForge, as they break down what’s really happening as the MCP protocol matures. We’ll cover: -Why MCP servers are exploding in number -The growing pains behind the protocol’s rapid adoption -How projects like ContextForge help developers manage, curate, and actually trust their MCP endpoints -What all of this means for building reliable agentic systems If you’re working with agents, tools, or anything MCP-adjacent, this one’s worth a watch!
Taming MCP Chaos with Mihai Criveti from IBM/ContextForge
www.linkedin.com
-
Langflow reposted this
IBM dropped CUGA, open-source enterprise agent to automate boring tasks 🔥 > given workspace files, it writes and executes code to accomplish any task 🤯 > comes with a ton of tools built for enterprise tasks, supports MCPs > plug in your favorite LLM 👏 here's a small demo where it retrieves info from a file, calculates revenue by writing code, and drafts an e-mail 🤯 they release code with Apache-2.0 license, a blog and a Space on Hugging Face 🙌🏻 you can run this locally release blog with the demo, code and more! https://lnkd.in/dG7_idBY
-
MCP has been around a year, but it wasn't the first thing to try to extend LLMs and it might not be the last. What do you think about the future of MCP? Also in the AI++ newsletter this week: * A deep dive into prompt caching - understand this and you'll save time and money! * A look at the best ways to get JSON output from models * Parsing PDFs into Markdown in Langflow * And more lessons from agent builders like you
-
MCP servers are inefficient and we can do better. At least that's what some people think, and they are building the tools to help improve the situation. Others say that MCP isn't bad, but there are bad MCP servers. Also in AI++ this week: ✨ new, leaderboard topping models 🤖 lessons from coding agents 📝 ways to improve your context
-
When building RAG systems, it helps to use tools that are vendor-agnostic and let you build using your data sources & LLMs of choice. David Jones-Gilardi is going to showcase how devs are using Langflow and open tools to move fast and build tailored enterprise-ready solutions ⚡️ Register now at: https://openr.ag/summit
-
-
The heart of RAG working is making sure that your documents and data can be ingested and converted into something useful for LLMs and Agentic systems 💾 Roy Derks is going to share how Docling tackles this problem & helps devs build fast, high-performance ingestion pipelines for their search systems 🔎 Register now at: https://openr.ag/summit
-