Anthropic just dropped a blog post that could finally fix MCP's biggest problem — the context window.
Instead of loading all your tools upfront and burning through tokens, the new code execution approach lets Claude interact with MCP servers as code APIs. This means tools load on-demand, data filters in the sandbox before reaching the model, and token usage drops from 150K to 2K.
The Chinese AI startup Moonshot AI’s new Kimi K2 Thinking model, has vaulted past both proprietary and open-weight competitors to claim the top position in reasoning, coding, and agentic-tool benchmarks.
Despite being fully open-source, the model now outperforms OpenAI’s GPT-5, Anthropic’s Claude Sonnet 4.5 (Thinking mode), and xAI's Grok-4 on several standard evaluations — an inflection point for the competitiveness of open AI systems.
Google Cloud has introduced a big update in a bid to keep AI developers on its Vertex AI platform for concepting, designing, building, testing, deploying and modifying AI agents in enterprise use cases.
LangChain demonstrates a coding CLI built using the deepagents package. This tool features integrated memory, allowing it to learn and retain instructions over time. Watch as they build and utilize custom agents with persistent memory profiles.
GitHub is giving developers access to third-party AI coding agents with the launch of a new “Agent HQ.” Instead of just using GitHub Copilot, developers will get to try OpenAI’s Codex, Anthropic’s Claude, Google’s Jules, xAI, and Cognition’s Devin within GitHub in the coming months.
Thesys C1 is a Generative UI API that transforms AI applications from text-based chat interfaces into dynamic, interactive experiences. Generate buttons, forms, dashboards, and charts directly from LLM outputs. Works with GPT-4, Claude, and any AI model. Integrates seamlessly with Vercel AI SDK and existing AI apps.
