Our open source Agent Chat UI now offers standardized support for file uploads! https://t.co/PTNeLInRrn
— LangChain (@LangChain) 20 mai 2025
Our open source Agent Chat UI now offers standardized support for file uploads!
CODE
-
LangChain Agent Chat UI Now Supports File Uploads
By
–
-
Agent Chat UI Launch with GitHub Repository
By
–
Agent Chat UI: https://
agentchat.vercel.app GitHub Repo: -
User enjoys new AI agent, previously used Claude and Codex for coding
By
–
Dream-O change la donne.
— VISION IA (@vision_ia) 20 mai 2025
Une nouvelle IA open source génère des images ultra-précises à partir de simples photos de référence.
Objets, visages, styles, scènes — tout est maîtrisé.
C’est plus qu’un outil visuel : c’est un moteur de narration visuelle à la demande.
Et ce n’est… https://t.co/6yumX0wD5v pic.twitter.com/Tlils3xNZ6Dream-O change la donne. Une nouvelle IA open source génère des images ultra-précises à partir de simples photos de référence.
Objets, visages, styles, scènes — tout est maîtrisé. C’est plus qu’un outil visuel : c’est un moteur de narration visuelle à la demande. Et ce n’est -
Gemini Diffusion: Faster Model Matches Advanced Coding Performance
By
–
Gemini Diffusion, our newest research model, is significantly faster than our fastest model so far AND matches its coding performance. By correcting errors as the model thinks, it is extremely fast for editing tasks like math and coding. pic.twitter.com/H811OrRebY
— Google AI (@GoogleAI) 20 mai 2025Gemini Diffusion, our newest research model, is significantly faster than our fastest model so far AND matches its coding performance. By correcting errors as the model thinks, it is extremely fast for editing tasks like math and coding.
-
Enterprise Agent Builder with Knowledge Base and MCP Actions
By
–
here’s a clean and easy to use enterprise agent builder with knowledge base, agent testing, and actions (email, calendar, etc) using MCP https://t.co/IKuVT9zO1g
— Yohei (@yoheinakajima) 20 mai 2025here’s a clean and easy to use enterprise agent builder with knowledge base, agent testing, and actions (email, calendar, etc) using MCP
-
Google’s AI Progress: 400M Users, 50x Token Growth
By
–
Google's progress in AI since last year: – The worlds strongest models, on pareto frontier
– Gemini app: has over 400M monthly active users
– We now process 480T tokens a month, up 50x YoY
– Over 7M developers have built with the Gemini API (4x) Much more to come still! -
LangGraph Platform Now Supports MCP Integration
By
–
LangGraph Platform Now Supports MCP! Every deployed agent on LangGraph Platform now exposes its own MCP endpoint. Leverage your agents as tools in any client supporting streamable HTTP for MCP— no custom code or infrastructure required. Docs: https://
langchain-ai.github.io/langgraph/conc
epts/server-mcp/
… -
Simula 67: First Language With Classes and Abstract Data Types
By
–
In May 1967, two computer scientists presented a paper about Simula 67, the first programming language to include abstract data types and classes: http://
bit.ly/2RqFkGn -
Keras Release: Model Sharding, Muon Optimizers, New Ops
By
–
New Keras release is out — includes saved model file sharding for very large models, the Muon optimizers, new ops and many performance improvements
-
BabyAGI 2 and MCPs: Shared Design Philosophies for Agent Tools
By
–
while there are lot of differences, just realized that babyagi 2 design had they key philosophies introduced in MCPs two months later: – manage plug-in tools separately
– add descriptions to tools for AI to use
– bundle tools as packs/servers