Project Polaris Replaces GPT-4 in GitHub Copilot Aug 2026
Microsoft unveiled Project Polaris at Build 2026: an in-house mixture-of-experts coding model that replaces GPT-4 Turbo as the GitHub Copilot default in August 2026.
Microsoft Ships Postgres for Cursor with Agent MCP
Microsoft published its first-party PostgreSQL extension to Open VSX on June 1, 2026, unblocking Cursor users and bundling a DBAgent MCP server so AI agents read live schema and EXPLAIN plans inline.
GitHub Copilot Switches to Usage-Based Billing Today
GitHub Copilot switches to usage-based billing on June 1, 2026, replacing flat-rate Pro and Business plans with metered completions and premium model requests.
Claude Code Proxy: Run on Kimi or ChatGPT Subscriptions
A developer-built tool called claude-code-proxy lets creators and developers route Claude Code through Kimi Code or ChatGPT Plus/Pro subscriptions instead of paying Anthropic API rates.
Cursor 3.6 Auto-Review Cuts Agent Approval Prompts
Cursor shipped auto-review mode today in version 3.6, a new run mode that lets the agent work for longer stretches with fewer approval prompts.
Claude Code 2.1.152: code-review fix, reload-skills, more
Anthropic shipped five Claude Code releases in six days, capped by v2.1.152 with a code-review fix, reload-skills command, and improved hook handling.
CUDA 13.3 Ships Python 1.0 + 15% LLM Inference Boost
CUDA 13.3 lands Python 1.0 stable, CompileIQ for 15% LLM inference speedups, and PyTorch/JAX zero-copy. What creative AI builders gain.
Reasonix: $12 DeepSeek Coding Agent vs $61 Claude Code
An open-source DeepSeek-native coding agent built around prefix-cache stability. A 435M-token session that costs $61 on Claude runs $12 on Reasonix.
Gemma 4 2B: Local Tool Calling and Code Review
Google's Gemma 4 E2B proves that a 2B parameter model can handle structured JSON output, tool calling, reasoning traces, and real code review -- all running locally at zero API cost.
CodeGraph MCP Cuts Claude Code Costs 35%
CodeGraph v0.9.4 is a free, open-source MCP server that pre-indexes your codebase into a semantic knowledge graph, cutting Claude Code costs 35% and tokens 57% across seven real-world benchmarks.
Claude Code 2.1.147 Ships /code-review With Effort Levels
Anthropic shipped Claude Code 2.1.147 on May 21 with a configurable-effort /code-review command and a May 22 hotfix 2.1.148 for a Bash regression.
Google AI Studio Adds Free Cloud SQL and Firestore
Google AI Studio added free Cloud SQL and Firestore on May 21 with a two-app Starter Tier for vibe-coded full-stack builds, no billing account required.
xAI Adds Grok Build to OpenCode for SuperGrok Subs
xAI on May 21, 2026 enabled SuperGrok and X Premium subscribers to use Grok Build, the company's terminal coding agent, directly inside OpenCode without an API key.
Sonar Brings Audio Search to AI Agents and Podcast Creators
Sonar entered public beta offering natural-language search across podcasts, news, earnings calls, and radio archives for AI agents. Free tier: 500 queries/month.
ElevenLabs Speech Engine Tutorial: Add Voice in 30 Min
Wrap an existing chat agent (Claude, GPT, Gemini) with ElevenLabs Speech Engine voice in roughly 30 minutes. Step-by-step tutorial covers Node and Python SDKs, WebRTC token flow, turn detection, interruption, and the upgrade path to ElevenAgents.
Migrate Claude or Gemini Agent to Google AX: Tutorial
Google open-sourced Agent Executor (AX), a distributed runtime that gives any AI agent durable execution, sandboxed isolation, and crash recovery. Here is the 30-minute migration path for an existing Claude Code, Cursor, or Gemini CLI workflow, end-to-end.
Secure Your Gemini API Key in 3 Steps
Google published a 3-step guide to locking down Gemini API keys with API restrictions, Secret Manager storage, and key hygiene to prevent billing abuse.
Inter-1 Streaming: Real-Time Behavioral AI for Live Video
Interhuman AI launched a streaming API for Inter-1 on May 20, bringing real-time behavioral signal detection from live video over WebSocket to developers building coaching and creator tools.
Claude Agents Get Self-Hosted Sandboxes and MCP Tunnels
Anthropic shipped self-hosted sandboxes (public beta) and private MCP tunnels (research preview) for Claude Managed Agents so tool execution and internal data access can stay on customer infrastructure.
NVIDIA Nemotron Diffusion: 3x Faster LLM Decoding
NVIDIA released the Nemotron-Labs-Diffusion family on Hugging Face, an open-weights LLM that switches between autoregressive, diffusion, and self-speculation decoding for 2.7x to 3.3x throughput gains.
Antigravity CLI Tutorial: Beat the June 18 Deadline
Gemini CLI stops serving Pro and Ultra subscribers on June 18, 2026. This tutorial walks through the full migration to Antigravity CLI in 30 minutes, including install, parity testing, async background agents, and how to keep CI pipelines from breaking.
Vercel Zero: A Programming Language Built for AI Agents
Vercel Labs just shipped Zero v0.1.3, an experimental programming language designed for AI coding agents rather than humans. Structured diagnostics and a broad standard library aim to cut wasted agent tokens.
Mini Shai-Hulud npm Attack Hijacks Claude Code Sessions
A May 19 npm supply-chain wave compromised 317 packages including timeago.js and the @antv ecosystem, rewriting .claude/settings.json to hijack Claude Code, Codex, and Cursor sessions.
Anthropic Acquires Stainless: What Claude SDK Devs Should Do
Anthropic acquired Stainless on May 18, 2026, the SDK and MCP server tooling company behind every official Claude API client library.