Claude Code and Claude Agent SDK cooked
CODE
-
MCP usefulness varies by tool integration and CLI capabilities
By
–
I think they is "some" MCP use cases. The ones where a good CLI tool exist + the models know how to use it well (gh is one of those) will make the MCP for those less useful. For everything else – e.g., Notion, HubSpot, Airtable, Calendars, Linear, … I think you will still want
-
CrewAI Multi-Agent Systems Course with Founder João Moura
By
–
New course announcement: Design, Develop, and Deploy Multi-Agent Systems with CrewAI, taught by @joaomdmoura, @crewAIInc Co-founder and CEO.
— Andrew Ng (@AndrewYNg) 11 novembre 2025
Multi-agent systems let you build AI teams that work together to automate complex workflows, similar to how human teams work.
CrewAI… pic.twitter.com/SdXvxnVk4eNew course announcement: Design, Develop, and Deploy Multi-Agent Systems with CrewAI, taught by @joaomdmoura
, @crewAIInc Co-founder and CEO. Multi-agent systems let you build AI teams that work together to automate complex workflows, similar to how human teams work. CrewAI -
Google AI agent builder vibe-coded, n8n remains relevant
By
–
Google’s AI agent builder looks like it was vibe coded. n8n is still not going anywhere.
-
Verdent Subagents for Automated Codebase Research and Improvement
By
–
Verdent Subagents can be called via @ tag and will be able to perform a broad range of different tasks, from summarising and performing research on the codebase, to suggesting improvements and verifying a proposed action plan.
-
Grok CLI Agent for Coding Tasks Announced
By
–
BREAKING : Grok Code command line Agent is coming! Besides Grok Code Remote, users will be able to run coding tasks from their local machines via CLI interface, too (not available yet). – "Install the Grok agent"
– "npm install -g @ xai-official/grok" -
xAI developing remote virtual environments for Grok Code tasks
By
–
BREAKING : xAI is working on Grok Code remote! Users will be able to create virtual environments and run Grok Code tasks directly from the web. It seems that both remote and local options will be available. December Hackathon prep?
-
Grok 4 Fast has 2M token context window, 5x ChatGPT, 2x Gemini
By
–
Context window comparison: • ChatGPT 5: 400,000 tokens
• Gemini 2.5 Pro: 1,000,000 tokens
• Grok 4 Fast: 2,000,000 tokens that’s 5x bigger than ChatGPT. 2x bigger than Gemini. load your entire codebase as one prompt. every doc. every conversation. every data point. no -
Grok 4 Fast’s 2 million token context window is a game changer
By
–
BREAKING: Grok 4 Fast just dropped a 2 million token context window. that’s not an upgrade. that’s a different game. load your entire codebase. your whole product docs. every customer conversation. not as attachments. as one prompt. no more “please summarize this first.” no
-
Kimi outperforms GPT-5 on key benchmarks like Humanity’s Last Exam
By
–
the benchmarks aren't close. they're embarrassing. > humanity's last exam: kimi 44.9%, beats closed models
> browsecomp (agentic web search): kimi 60.2% vs gpt-5's 54.9%
> gpqa diamond: 85.7% vs gpt-5's 84.5%
> swe-bench verified: 71.3% (coding tasks)
> artificial analysis