Vercel AI Gateway and AWS Kiro Crew Push Composable Multi-Model Agent Stacks

Vercel AI Gateway adds GLM-5.3 Flash, Qwen 3.8 Max and Gemini 3.7 Flash as AWS Kiro Crew and Claude agents expand multi-model stacks

Today’s releases underscore a clear shift toward gateway-mediated access and agent orchestration. Builders now have fresh options for routing inference through unified endpoints while agent frameworks mature toward reliable, multi-step execution. These updates arrive amid broader…

OpenAI Cuts Cursor GPT After SpaceX as Editors Models and Harnesses Split

OpenAI ends Cursor GPT access after SpaceX as GitHub Copilot, Alibaba Qwen, and LangChain split editor models and harnesses

The last 48 hours were not a quiet weekend for builders. The story that actually moves shipping calendars is contractual, not architectural: OpenAI told SpaceX it will terminate Cursor’s direct GPT supply, using a change-of-control window after Anysphere closed into the…

IBM Granite 4.2 llama.cpp and Claude Code make hybrid local agents shippable

IBM Granite 4.2, llama.cpp 0.3.0 multimodal inference, and Claude Code 2.1.246 enable hybrid local AI agents for developers.

Builders spent August chasing cheaper, longer-running agents. Today the stack snapped into focus. IBM put native reasoning and sandbox-trained tool use into downloadable dense models you can run on-prem or at the edge. ggml’s llama.cpp finally treated vision and audio as…

Cursor Origin, RAGFlow, Haystack, and Agno rebuild infrastructure under agents

Cursor Origin, RAGFlow 0.27, Haystack CompactionHook, and Agno 3.0 rebuild agent infrastructure for git, retrieval, context, and tools.

The interesting work this week is happening under the agent, not in another chat demo. Cursor is treating source control as part of the runtime: Origin hosts git remotes in the same Codebase tab where cloud agents already open PRs, while mirrored GitHub projects keep GitHub as…

OpenAI Assistants API Hard-Stops Tomorrow as Haystack Agno Langfuse Harden Agent Plumbing

News graphic: OpenAI Assistants API hard-stops August 26 while Haystack, Agno, and Langfuse upgrade agent infrastructure

The last 48 hours were not about a new flagship model. They were about the plumbing that decides whether your agents survive contact with production. OpenAI’s Assistants API — the beta that taught a generation of teams to think in Assistants, Threads, and Runs — reaches a hard…

GitHub Copilot Cursor and VS Code agents go always-on as OpenAI keeps ZDR

GitHub Copilot, Cursor, and VS Code agents go always-on while OpenAI previews Private Safety Processing to keep Zero Data Retention

Coding agents left the sidebar this week. GitHub put Copilot’s cloud agent inside Microsoft Teams conversations. Cursor taught always-on agents to wake on PRs and Slack, farm work to isolated VMs, and keep a goal until CI is green. VS Code 1.134 split the agent harness into its…