Cursor now able to use 80% of Figma via MCP pic.twitter.com/pDgnVpgold
— Linus ✦ Ekenstam (@LinusEkenstam) 16 mars 2025
Cursor now able to use 80% of Figma via MCP
By
–
Cursor now able to use 80% of Figma via MCP pic.twitter.com/pDgnVpgold
— Linus ✦ Ekenstam (@LinusEkenstam) 16 mars 2025
Cursor now able to use 80% of Figma via MCP

By
–
[ SOVEREIGN AGENTIC AGI ALPHA ] Pre-Alpha Version: https://
montrealai.github.io/muzeromctsllma
gentv0.html
… CA: tWKHzXd5PRmxTF5cMfJkm2Ua3TcjwNNoSRUqx6Apump $AGIALPHA is History. #AGI $AGIALPHA #AGIALPHA
By
–
you could try SWE Agent https://
swe-agent.com/latest/
By
–
smolagents has code execution in @e2b sandboxes Docs here:
By
–
The Responses API makes it easy for developers to build very useful agentic experiences. It comes with built-in tools, starting with web search, file search, and computer use. Super excited to see what applications it will unlock! https://t.co/YpMHUo0Onr
— Greg Brockman (@gdb) 16 mars 2025
The Responses API makes it easy for developers to build very useful agentic experiences. It comes with built-in tools, starting with web search, file search, and computer use. Super excited to see what applications it will unlock!
By
–
More context: in ToolCallingAgent, smolagents always needs a tool call, so removing the necessity of calling a tool would just break the lib's logic. Indeed this is on vLLM's side to integrate!

By
–
people are saying 2025 is the year of agents… agents have been here for the past year. building agents requires new tools and a new mental model Replit, LinkedIn, Uber, Elastic are using LangGraph/LangSmith to help power their agents https://
blog.langchain.dev/top-5-langgrap
h-agents-in-production-2024/
…
By
–
fastest way to get started with agents in javascript🚤
— Harrison Chase (@hwchase17) 15 mars 2025
prebuilt templates, UI, helpful installer… it's got it all! https://t.co/2NMNddrHqN
fastest way to get started with agents in javascript prebuilt templates, UI, helpful installer… it's got it all!

By
–
How do I speed up my agent? I get asked this question a bunch, so I wrote a quick blog on it. Techniques we see getting used: – Identifying where the latency is coming from
– Changing the UX to reduce the “perceived” latency
– Making fewer LLM calls
– Speeding up LLM calls
–

By
–
smolagents now support vLLM! As one of the most popular local inference solutions, the community had been asking us to integrate vLLM: after a heavy refactoring of our LLM classes, we've just released smolagents 1.11.0, with a brand new VLLMModel class. Go try it and tell us