developer-tools

Mistral AI released Vibe 2.0, a terminal-native coding agent powered by Devstral 2, adding custom subagents, multi-choice clarifications, and slash-command skills. Devstral 2 API pricing is now $0.40/M input tokens and $2.00/M output tokens, with a smaller variant at $0.10/$0.30 per million tokens.

Replit is now available as a direct integration within Claude, according to Replit. The integration allows users to design applications in Claude Design using natural language, then send projects directly to Replit for development and deployment without manual copy-pasting or context switching.

Google is shutting down Gemini CLI and Gemini Code Assist for GitHub for consumer-level users on June 18, 2026, as it consolidates development tools into its Antigravity CLI platform. Enterprise users will retain access to Gemini Code Assist unchanged.

GitHub has updated Copilot CLI to reduce unnecessary handoffs between AI models. The improvement delivers faster command execution through better orchestration logic, implemented without adding new user configuration options.

GitHub has updated the orchestration logic in Copilot CLI to make it more selective about when to delegate tasks between language models. The changes reduce unnecessary handoffs and improve response times without introducing additional configuration settings.

Replit has launched SEO Agent, an automated tool that scans deployed applications for search optimization issues and can automatically apply fixes. The agent checks crawlability, meta tags, semantic structure, and generates recommendations ranked by impact, with changes applied as separate reviewable tasks.

OpenCode v1.15.13 introduces custom session metadata storage through its API and SDK. The release fixes a bug where Anthropic's Opus 4.7+ adaptive reasoning returned empty thinking blocks instead of summarized thinking.

Vercel released AI SDK version 4.0.0-canary.69 with breaking changes to xAI integration. The update deprecates the searchParameters option for xAI live search, replacing it with dedicated web_search and x_search agent tools, and adds image search capability through a new enableImageSearch parameter.

Vercel released version 4.0.0-canary.75 of its AI SDK Google package on May 30, adding support for three new Google models: gemini-embedding-2, deep-research-max-preview-04-2026, and deep-research-preview-04-2026. The update enables developers to integrate Google's latest embedding and deep research capabilities into applications built with the Vercel AI SDK.

Cline v3.86.0 adds provider support for Claude Opus 4.8, including 1M-context variants where available, and Moonshot Kimi K2.6 models. The update also fixes prompt-cache support display for Qwen 3.7 Max.

Anthropic released version 0.105.0 of its Python SDK on May 28, 2026, adding support for the Claude Opus 4-8 model. The update includes mid-conversation system blocks and detailed output token usage tracking.

Google has raised Gemini usage limits in its Antigravity coding tool by 3x twice within one week, responding to developers who hit new compute-based quotas within hours. The company also reset weekly quotas for all paid users twice, though limits remain lower than pre-restriction levels.

Anthropic released version 0.104.0 of its Python SDK on May 21, 2026. The update adds support for a thinking-token-count beta feature that provides estimated token counts in thinking block deltas when streaming responses from reasoning models.

Replit today launched self-serve Enterprise, allowing organizations to purchase and configure an Enterprise account with SSO, SCIM, and RBAC in minutes without sales calls. The credit-based model provides unlimited seats, with all spending pooled across Replit Agent, Deployments, and Storage.

Developer Simon Willison released version 0.32 of the llm-gemini plugin, which adds support for Google's Gemini 3.5 Flash model. The plugin enables command-line access to Google's Gemini model family through the LLM tool.

Google announced Antigravity 2.0 at I/O 2026, transforming its coding tool into a full developer platform with a revamped desktop app supporting multi-agent orchestration, a new Go-based CLI, and an SDK for custom agents. The company introduced a $100/month AI Ultra tier and confirmed Gemini CLI will shut down for consumers on June 18, 2026.

Amazon Bedrock now supports programmatic tool calling (PTC), a technique that allows LLMs to generate Python code for multi-step tool orchestration rather than making sequential API calls. AWS offers three implementation paths: self-hosted Docker sandboxes on ECS, managed execution via Amazon Bedrock AgentCore Code Interpreter, and Anthropic SDK-compatible proxy integration.

GitHub has launched remote control capabilities for Copilot sessions, now generally available on github.com and GitHub Mobile. Developers can initiate coding sessions in VS Code or the command line and continue them on mobile devices.

Cline released CLI version 3.0.6 with updated ChatGPT provider model list. The patch adds support for codex variants and three new GPT-5 series models: gpt-5.2, gpt-5.4, and gpt-5.4-mini.

Replit released its first iPhone app update in four months after resolving App Store review issues with Apple. The update brings Agent 4, the company's latest AI coding assistant, along with parallel agent support and cross-workspace project viewing.

Microsoft is removing Claude Code access from its Experiences + Devices division by June 30, 2026, redirecting thousands of engineers to GitHub Copilot CLI instead. The decision follows six months of Claude Code proving more popular than Microsoft's own coding tool among internal developers.

OpenAI has implemented a custom sandbox for its Codex coding agent on Windows after determining that existing Windows isolation tools—AppContainer, Windows Sandbox, and Mandatory Integrity Control—could not adequately balance safety and functionality. The solution uses synthetic SIDs and write-restricted tokens to constrain file writes and network access without requiring administrator privileges.

OpenAI developed a custom sandbox implementation for its Codex coding agent on Windows after existing tools like AppContainer and Windows Sandbox failed to meet requirements. The solution uses synthetic SIDs and write-restricted tokens to constrain file writes and network access without requiring administrator privileges.

Apple released Xcode 26.5 with two new Coding Intelligence features: the ability to queue multiple messages to AI coding assistants without waiting for responses, and agent support for asking clarifying questions before executing tasks. The update builds on agentic coding capabilities introduced in Xcode 26.3, which allowed developers to integrate tools like OpenAI Codex and Anthropic's Claude directly into the IDE.

A GitHub engineer has developed an extension using GitHub Copilot CLI that procedurally generates roguelike dungeons from existing codebases. The project demonstrates practical applications of GitHub's AI-powered command-line tool for creative development tasks.

Cursor has integrated its AI code editor into Microsoft Teams, allowing developers to delegate coding tasks by mentioning @Cursor in any Teams channel. The integration automatically selects repositories and AI models, reads thread context, and generates pull requests for team review.

GitHub has optimized token usage in its production agentic workflows that run on every pull request. The company instrumented its own Copilot workflows to identify inefficiencies and built agents to address them, aiming to reduce accumulated API costs.

Google is developing an intermediate subscription tier called 'AI Ultra Lite' to slot between its $20 Pro and $250 Ultra plans, according to code discovered in the Gemini macOS app. The company is also preparing a usage dashboard showing token budgets across five-hour and weekly limits.

Augment Code has released Cosmos into public preview, positioning it as an operating system for agentic software development. The platform coordinates AI agents across the full software development lifecycle with shared memory, multi-model routing via their Prism system that claims 20-30% token savings, and what the company calls specialized agents that learn from team feedback.

OpenAI added a /pet feature to its Codex Mac app that displays animated companion creatures in the interface. Users can choose from preset options or create custom pets that provide status updates while Codex runs in the background.

Mistral AI has integrated its Medium 3.5 model into Vibe for remote coding agent functionality. The company also launched a new Work mode in Le Chat designed for complex tasks, though specific technical details remain undisclosed.

Microsoft's GitHub is ending flat-rate billing for Copilot on June 1, 2026, switching to usage-based metered tokens after acknowledging the request-based model is no longer sustainable. Copilot Pro subscribers ($10/month) will receive 1,000 GitHub AI Credits monthly, with each credit worth $0.01.

GitHub Copilot transitions to token-based pricing effective June 1, 2026, replacing its premium request unit system. Base subscription prices remain unchanged at $10/month for Pro and $39/month for Pro+, but users now receive equivalent monthly AI Credits that deplete with usage—and service stops when credits run out.

Cline, the AI coding assistant, released v3.81.0 with support for GPT-5.5 for OpenAI Codex subscription users. The update also removes hardcoded welcome banners and adds enhanced memory diagnostics including heap snapshots for debugging out-of-memory issues.

Anthropic confirmed that widespread complaints about Claude Code quality degradation were caused by three separate bugs in the coding assistant's harness, not the underlying models. One critical bug caused Claude to clear its thinking context every turn in sessions that had been idle for over an hour, making it appear forgetful and repetitive.

Anthropic has released version 0.97.0 of its Python SDK, introducing CMA Memory as a public beta feature. The update includes bug fixes for API spec errors, restored missing features, and performance improvements for multipart file requests.

GitHub has updated Copilot Chat on github.com with improved stack trace recognition. The enhancement helps developers identify error root causes faster when debugging by more reliably parsing pasted stack traces.

Replit has introduced Security Agent, an AI-powered tool that performs comprehensive security reviews of codebases in under an hour. The agent uses a hybrid approach combining LLMs with Semgrep and HoundDog.ai, and according to recent research can identify up to 93.3% of false positives from traditional static analysis tools.

Google has released a preview of Android CLI, a command-line tool designed specifically for AI agents to build Android applications. Google claims the tool reduces token usage by 70 percent and cuts task completion time to one-third compared to traditional methods.

Anthropic has launched a cloud service called routines that allows Claude Code users to run automated AI tasks on company infrastructure. Daily limits range from 5 routines for Pro users to 25 for Team/Enterprise customers.

Anthropic has released routines for Claude Code, allowing automated bug fixes, code reviews, and deployment monitoring to run on cloud infrastructure without requiring users' local machines. The feature is available in research preview with daily limits of 5-25 runs depending on subscription tier.

Anthropic launched repeatable routines for Claude Code in research preview, allowing developers to schedule automated tasks that run on cloud infrastructure without requiring their local machine to be online. Pro users get 5 daily routines, Max users get 15, and Team/Enterprise users get 25.

Anthropic has launched Ultraplan, a new feature for Claude Code that offloads programming task planning to the cloud. The feature enables developers to initiate planning jobs from the terminal while the planning executes in the browser, supporting inline comments, emoji reactions, and revision requests on individual plan sections.

GitHub has added a feature called Rubber Duck to Copilot CLI that queries multiple AI model families to provide alternative perspectives on code suggestions. The feature acts as a second opinion mechanism, allowing developers to compare recommendations from different model architectures.

Cursor released version 3 of its AI coding tool with a complete interface redesign built around running multiple AI agents in parallel rather than individual code editing. The new "agent-first" interface allows developers to launch agents from desktop, mobile, web, Slack, GitHub, and Linear, with seamless switching between cloud and local environments.

GitHub's Applied Science team deployed coding agents to automate parts of their own development workflow, testing how AI agents can handle increasingly complex programming tasks. The experiment reveals practical insights into agent-driven development patterns and limitations.

OpenAI released a plugin that embeds its Codex coding assistant directly into Anthropic's Claude Code, the market-dominant code IDE. The plugin offers standard code review, adversarial review, and background task handoff capabilities, requiring only a ChatGPT subscription or OpenAI API key.

OpenAI is releasing a set of open-source prompts developers can use to make their applications safer for teens. The policies, designed to work with OpenAI's gpt-oss-safeguard model, address graphic violence, sexual content, harmful body ideals, dangerous activities, and age-restricted goods.

Anthropic has released 'auto mode' for Claude Code, a permissions system that sits between conservative defaults and fully disabled safeguards. The feature uses a classifier to automatically approve safe actions like file writes and bash commands while blocking potentially destructive operations.

Anthropic has added "channels" to Claude Code, enabling Claude to respond to incoming messages, webhooks, and notifications asynchronously without user intervention. The research preview supports Telegram and Discord with custom channel support, running through MCP servers with two-way communication.