Kinetic Agent

[Zainab Ayaz @ZainabAyaz_MLE]

Over at @KineticLabs_ ,open source release week continues! `create_react_agent` now supports a `post_model_hook` argument. This hook is great for:

🚶‍human in the loop interactions
🚧 guardrails
💬 message processing

[Factory @FactoryAI]

Software development is more than just coding.

Introducing Droids -- the world's first software development agents. 🤖

Starting today, Droids are available for general access.

Factory integrates with your entire engineering system (GitHub, Slack, Linear, Notion, Sentry) and serves that context to your Droids as they autonomously build production-ready software.

Factory is the first platform that allows you to work with agents: local + synchronous and remote + asynchronous.

[Kinetic Agent @KineticLabs_]

We’re excited to be a part of #SnowflakeDevDay on June 5 in San Francisco! Get the latest in AI/ML, join a GenAI bootcamp, and connect with thousands of other builders. Register for free:
https://t.co/o8dCnb88c8

[Kinetic Agent @KineticLabs_]

💻 New built-in code interpreter and remote MCP tools in OpenAI!

OpenAI released new built-in tools in its Responses API, including a code interpreter for sandboxed code
execution and a remote MCP tool for model-generated calls to MCP servers.

Try them out in Kinetic AI! 🧵

[Harrison Chase @hwchase17]

We're doing some LangChain office hours this Thursday morning in New York - come say hi!

https://t.co/oueiFlijBc

[LangChain @LangChain]

🤖🎓 PhiloAgents

Build AI agents that impersonate philosophers with LangGraph in this OSS repo covering RAG implementation, real-time conversations, and system architecture with FastAPI & MongoDB integration.

Start building philosophical agents! 🚀
https://t.co/RAsGcr523B

[Austin Vance @austinbv]

Not all SWAG is created equal! My boys insisted brining their LangChain parrots camping this weekend!

Does the parrot have a name?

[LangChain @LangChain]

🔍🤖 UQLM: Hallucination Detection Library

UQLM quantifies uncertainty in LLMs to detect hallucinations using multiple scoring methods. With native LangChain integration, it enables developers to build more reliable AI applications.

Check it out 🚀
https://t.co/g3wjZ0sKRn

[LangChain @LangChain]

🔥 Hear how @Cisco automated 60% of 1.8 million support cases with LangGraph, LangSmith, and LangGraph Platform 🔥

In his LangChain Interrupt talk, Carlos Pereira, Fellow & Chief Architect at Cisco, shares Cisco’s blueprint for transforming customer experience with AI agents.

In this video, you’ll learn about:

- How Cisco’s Customer Experience team identifies and prioritizes high-impact AI use cases
- Their supervisor architecture that routes complex queries across specialized agents
- How LangGraph, LangGraph Platform, and LangSmith power the development and continuous improvement of these agents

Watch the video: https://t.co/MQl2TaXtkX

[LangChain @LangChain]

🔍🤖 II-Researcher

A research assistant that combines search providers and web scraping with LangChain's text processing functionality to tackle complex questions. Features flexible LLM support and comprehensive data gathering capabilities.

Explore on GitHub! 📚
https://t.co/6CkPizGjtr

[LangChain @LangChain]

🤖💻 LlamaBot: AI Web Dev Assistant

Meet the AI coding agent that generates HTML, CSS, and JavaScript through natural language chat, featuring live preview capabilities. Built with LangChain's LangGraph and LangSmith for intelligent web development.

Check it out! 🔗 https://t.co/MtUTsGPrDN

[Tarun Jain @TRJ_0751]

4 AM Club👋

Was working on crazy side project to setup Hybrid search using @qdrant_engine latest miniCOIL using @langchain

Tech Stack Sneak peak: LangGraph, FastEmbed, Qdrant, SambaNova & Opik

The 2nd part of the Advanced Retriever technique blog series will be out soon👀

[Tavily @tavilyai]

The NYC tech ecosystem is more vibrant than ever! 🚀

More than 100 builders and founders gathered in our NYC office for a vibrant night of exploration.

Thank you @hwchase17, @rweiss57, Deepak Bapat and the teams at @langchain & @trytabs for bring this meetup to life!

[Sydney Runkle @sydneyrunkle]

🔍 You can now use builtin provider tools like web search and remote MCP with LangGraph!

[Sequoia Capital @sequoia]

If you interact with a chat agent, it's usually a one-to-one experience—you're doing one thing at a time.

With ambient agents, however, there can be thousands running in the background, dramatically scaling our ability to leverage AI.

@langchain's @hwchase17 at AI Ascent.

[Amy Xiao @amyxst]

Built this fun video chat app to celebrate and explore the recordings from @langchain's first AI agent conference! Chat with all 18 amazing talks

Made with @CloudglueDev for video understanding & @OpenAI GPT-4.1 mini for reasoning

Queries to try:
- "What were the biggest themes on AI agents from Interrupt this year?"
- "Give me the key launches announced in a table"
- "Render any cool code snippets"

Try it out :) https://t.co/LK2dJSO1x5
(If there's sufficient interest, I'll keep it around)

Congrats to the LangChain team for an amazing first conference!

[Harry Zhang @zhanghaili0610]

Thrilled to have been part of AiDD 2025 in Shanghai! It was an absolute joy presenting "Building Ambient Agents with LangGraph". 🌟

Loved sharing insights on HITL techniques powered by @langchain. Hope the session sparked ideas and offered tips for your amazing projects! 💡

[Chester Curme @chester_curme]

🧠 Claude 4

Anthropic just announced its next generation of Claude models, Sonnet and Opus 4, offering new capabilities and representing a significant upgrade to Sonnet 3.7.

Big release week so far!

[Chester Curme @chester_curme]

💻 New built-in code interpreter and remote MCP tools in OpenAI!

OpenAI released new built-in tools in its Responses API, including a code interpreter for sandboxed code execution and a remote MCP tool for model-generated calls to MCP servers.

Try them out in LangChain! 🧵

[Qdrant @qdrant_engine]

⚡️ Fast Multi-Document RAG using Qdrant, @SambaNovaAI, @deepseek_ai, and LangGraph

In Part 1 of his new series, @TRJ_0751 shows how to build a high-speed, memory-efficient RAG system that can handle multiple documents at a large scale.

➡️🧠 32x memory savings with Binary Quantization
➡️ Fast, focused LLM responses via DeepSeek-R1
➡️ Modular orchestration with LangGraph by @langchain

👉 Read the full blog: https://t.co/iFAyq0Bn71