Claude Python and TypeScript SDKs add built-in computer and browser use toolsets
Claude's Python and TypeScript SDKs now include built-in toolsets for computer use and browser use, running the execution loop and sending actions directly to drivers.
Claude's Python and TypeScript SDKs now include built-in toolsets for computer use and browser use, running the execution loop and sending actions directly to drivers.
GitHub has made local sandboxing generally available for GitHub Copilot, isolating command execution with granular controls over files, network access, credentials, and system capabilities.
The tool is designed to help developers build intuition for the model's bidirectional interaction and its ability to delegate tasks to other models or agents.
The tool allows developers to explore, visualize, and run reinforcement learning environments across OpenEnv, Harbor, MiMo, Verifiers, and NeMo Gym, which span over 12 million task entries on Hugging Face Hub.
DAIR.AI has released MCP tools that connect Codex, Claude Code, and Grok Bot to an index of curated AI research papers for search, summarization, and literature surveys.
OpenAI has launched the Decisions API in public beta for all developers, stating it allows applications to select models, tools, or actions up to 10 times faster than GPT-6 Luna through the Responses API.
OpenAI has consolidated its five paid API usage tiers into three—Build, Launch, and Grow. Qualifying for Grow, the new highest tier, now requires $500 in total API payments instead of $1,000.
Replit now supports context across all user projects within chat. Users can prompt Replit to locate existing projects, use one project as a reference to modify another, and execute edits as background tasks.
OpenAI Developers says the Codex CLI update includes /theme, managed worktrees, in-terminal Mermaid and LaTeX, collapsible diffs and tool output, and dedicated areas for status, hints, and keyboard shortcuts.
OpenAI Developers says Codex CLI now has a full-screen terminal interface with improved readability and ways to manage parallel work.
Developers can submit a Claude plugin, follow its review, and view usage in a new portal. ClaudeDevs says plugins package MCP and skills, and that MCP usage across Claude products is up 110x this year.
Cursor says the update reduces Security Reviewer's average time to 3.8 minutes from 4.8 minutes.
A new Prompt Caching Dashboard on platform.openai.com tracks cache-hit rates. A diagnostics API identifies changes that prevented cache reuse and estimates how many tokens were affected.
The release also includes transcript search, mouse copy, an F8 voice toggle and /voice settings, plus a /usage dashboard for tokens, plugins, and skills.
Command Code can create or switch Git worktrees with /worktree and run parallel sessions, each on its own branch.
StepFun provides a bash script to install Step Code on macOS, Linux, or WSL. On Windows, it recommends WSL and says PowerShell support is currently in beta.
StepPage publishes a local static site to a shareable URL with one command, with version management and rollback built in so development, debugging, and delivery can stay in the same terminal.
Worker Previews gives an agent a production-like environment for every change it makes.
Databricks says DevHub gives developers ready-to-use templates, documentation, step-by-step guidance, and agent prompts that can be copied into Cursor, Claude Code, Codex, or another coding agent.