developmentstoday

Ask DT AI Audio Brief Videos Podcast +

Ask DT AI Audio Brief Videos Podcast

HomeTagsdeveloper tools

#developer tools

All articles tagged with "developer tools"

Company

About Us
Advertise
Contact
Editorial Policy

Legal

Terms of Service
Privacy Policy
Cookie Policy
AI & Ethics Policy
Do Not Sell My Info
FAQ
Site Map

Discover

Newsletter
Ask DT AI
Audio Brief
Videos
Podcast
DT Premium

Connect

Twitter / X
Facebook
LinkedIn
YouTube
Instagram
TikTok
Flipboard
RSS Feed

© 2026 Developments Today. All rights reserved.

developer tools Articles | Developments Today

Image description

Microsoft is pulling internal Claude Code licenses and steering developers toward Copilot CLI

Microsoft is reportedly canceling most internal Claude Code licenses.
The change affects the Experiences and Devices group and is expected to take effect by late June.
The supplied report says strategic consolidation and fiscal-year cost savings are both factors.

DE

DT Editorial Team·May 15, 2026·via the-decoder.com

More in AI & Robotics→

Work with Codex from anywhere

Codex comes to the ChatGPT mobile app, extending agent workflows beyond the desktop

OpenAI says Codex is now available in preview in the ChatGPT mobile app.
Users can review threads, approvals, outputs, diffs, and test results from a phone.
OpenAI says work still runs on trusted machines while the app syncs live session state.

DE

DT Editorial Team·May 15, 2026·via openai.com

More in AI & Robotics→

Our response to the TanStack npm supply chain attack

OpenAI details limited fallout from TanStack supply-chain attack and orders macOS app updates

OpenAI says two employee devices were impacted by the TanStack npm compromise.
The company reported limited credential exfiltration from a small set of internal repositories.
OpenAI said it found no evidence of customer-data exposure, production compromise, or altered software.
All macOS users of OpenAI apps are being told to update by June 12, 2026 because of certificate changes.

DE

DT Editorial Team·May 14, 2026·via openai.com

More in AI & Robotics→

Building a safe, effective sandbox to enable Codex on Windows

OpenAI details the Windows sandbox built to constrain Codex

OpenAI says Codex on Windows previously forced users into frequent approvals or unrestricted access.
The company built a custom sandbox because existing Windows isolation tools did not meet its requirements.
The sandbox is designed to limit writes to the workspace and block internet access unless allowed.
OpenAI frames operating-system enforcement as essential to making coding agents both useful and safe.

DE

DT Editorial Team·May 13, 2026·via openai.com

More in AI & Robotics→

Spotify opens a new lane for AI-made audio with personal podcast publishing tool

Spotify introduced a command-line tool called Save to Spotify.
The tool is designed for AI agents such as OpenClaw, Claude Code, and OpenAI Codex.
Users can generate private audio briefings and save them directly into their Spotify library.

DE

DT Editorial Team·May 7, 2026·via theverge.com

DE

DT Editorial Team·May 4, 2026·via the-decoder.com

DE

DT Editorial Team·May 4, 2026·via the-decoder.com

DE

DT Editorial Team·May 3, 2026·via artificialintelligence-news.com

DE

DT Editorial Team·Apr 26, 2026·via openai.com

DE

DT Editorial Team·Apr 25, 2026·via openai.com

DE

DT Editorial Team·Apr 25, 2026·via the-decoder.com

DE

DT Editorial Team·Apr 21, 2026·via openai.com

DE

DT Editorial Team·Apr 17, 2026·via techcrunch.com

DE

DT Editorial Team·Apr 16, 2026·via the-decoder.com

DE

DT Editorial Team·Apr 16, 2026·via openai.com

DE

DT Editorial Team·Apr 15, 2026·via techcrunch.com

DE

DT Editorial Team·Apr 13, 2026·via techcrunch.com

DE

DT Editorial Team·Apr 12, 2026·via openai.com

DE

DT Editorial Team·Apr 12, 2026·via the-decoder.com

DE

DT Editorial Team·Apr 3, 2026·via blog.google

1
2
Next

More in News→

Image description

OpenAI’s Symphony Pushes AI Agents Closer to Self-Managed Software Work

OpenAI released Symphony, an open-source specification for agent-managed software workflows.
Agents can pull unblocked tickets directly from a task tracker such as Linear.
The system is designed to shift humans from session management toward review and judgment.

More in AI & Robotics→

Microsoft Reverses Course After VS Code Quietly Added Copilot as a Commit Co-Author

VS Code was found adding a hidden “Co-Authored-by Copilot” line to some commits, even with AI features disabled.
A Microsoft developer said the behavior was a mistake and that the default would be reverted in version 1.119.
The incident raised concerns about attribution, compliance, and trust in AI-powered developer tools.

More in AI & Robotics→

GitHub Copilot’s Shift to Per-Token Pricing Could Redefine How Developers Budget for AI

AI News reports that GitHub Copilot will move to token-based charging from June 1, 2026.
The change would replace Copilot’s flat-rate subscription model with usage-based billing.
A metered model could alter developer behavior, budgeting, and enterprise governance around AI coding tools.

More in AI & Robotics→

Speeding up agentic workflows with WebSockets in the Responses API

OpenAI Says Persistent WebSocket Sessions Cut Agent Loop Latency by Roughly 40%

OpenAI says agent loops using the Responses API became roughly 40% faster end to end.
The company says inference speed gains made API overhead a much larger bottleneck.
Persistent WebSocket sessions let OpenAI keep state and caching attached to a connection.

More in AI & Robotics→

How to get started with Codex

OpenAI Publishes a Starter Guide for Codex as It Pushes Practical Onboarding for AI Workflows

OpenAI published a practical getting-started guide for Codex through OpenAI Academy.
The guide emphasizes local project folders, threads, and explicit permission controls.
Its recommended workflow favors small supervised tasks and gradual trust-building.

More in AI & Robotics→

Image description

OpenAI Pushes Further Into Agentic Workflows With GPT-5.5 Launch

OpenAI launched GPT-5.5 and GPT-5.5 Pro for longer, tool-using workflows.
The company says the model is stronger at coding, knowledge work, computer use, and early scientific research.
API access was added on April 25, 2026, with a reported one million token context window.
Higher pricing puts pressure on OpenAI to prove that better task completion offsets higher model costs.

More in AI & Robotics→

Scaling Codex to enterprises worldwide

OpenAI launches Codex Labs as enterprise adoption of Codex jumps past 4 million weekly users

OpenAI says Codex usage rose from more than 3 million to more than 4 million weekly developers in roughly two weeks.
The company is launching Codex Labs to help enterprises move from pilot usage to structured deployment through workshops and working sessions.
OpenAI is also partnering with major global systems integrators to scale implementation capacity across large organizations.

More in AI & Robotics→

Sources: Cursor in talks to raise $2B+ at $50B valuation as enterprise growth surges | TechCrunch

Cursor Said to Pursue Funding Round That Could Value AI Coding Startup at $50 Billion

TechCrunch reported Cursor is nearing a funding round of at least $2 billion.
The proposed deal would value the company at $50 billion before the new capital injection.
Cursor reportedly expects to end 2026 with an annualized revenue run rate above $6 billion.
The company has recently reached slight gross margin profitability through a mix of proprietary and lower-cost models.

More in News→

OpenAI updates Agents SDK with new sandbox support for safer AI agents

OpenAI Adds Sandboxed Execution to Its Agents SDK

OpenAI added native sandbox support to its Agents SDK.
The update includes MCP tool usage, shell execution, and apply-patch editing.
Workspace manifests can describe local files and cloud storage.

More in AI & Robotics→

The next evolution of the Agents SDK

OpenAI Pushes Agents Closer to Production With Native Sandboxes and a Model-Native Harness

OpenAI added native sandbox execution and a model-native harness to the Agents SDK.
The update targets long-running agent workflows involving files, tools, and code edits.
It reflects a broader shift from agent demos toward deployable infrastructure.

More in AI & Robotics→

OpenAI ChatGPT website displayed on a laptop screen is seen in this illustration photo.

OpenAI expands its Agents SDK with sandboxing and workspace controls for enterprise deployments

OpenAI added sandbox integration to its Agents SDK.
The update is designed to help enterprises constrain agent access to files, code, and tools.
A new harness is intended to support long-horizon agents running on frontier models.
The company says the SDK will continue to expand over time.

More in News→

Vercel CEO Guillermo Rauch signals IPO readiness as AI agents fuel revenue surge | TechCrunch

Vercel Signals It Is Operating Like a Public Company as AI-Era Demand Accelerates

Vercel’s CEO said the company is already operating with the discipline of a public company.
Reported revenue run rate rose from $100 million in early 2024 to $340 million by late February 2026.
The company says AI-generated apps and agents are expanding demand for deployment infrastructure.

More in News→

Abstract blurred gradient of blue and yellow hues sweeping diagonally across the frame, creating a soft, glowing transition.

OpenAI Rotates macOS Signing Certificates After Axios Supply-Chain Incident

OpenAI said a malicious Axios version ran in a GitHub Actions workflow used in macOS app signing.
The company found no evidence that user data, internal systems, intellectual property, or shipped software were compromised.
OpenAI is rotating certificates and requiring updates for ChatGPT Desktop, Codex App, Codex CLI, and Atlas before May 8, 2026.

More in AI & Robotics→

Claude Code's new Ultraplan feature moves task planning to the cloud

Anthropic Moves Claude Code Planning Into the Cloud With Ultraplan Preview

Ultraplan shifts Claude Code planning from the terminal into a browser-based cloud workflow.
Users can comment on individual plan sections and execute the final plan in the browser or terminal.
The preview requires a web-enabled Claude Code account, a GitHub repository, and version 2.1.91 or later.

More in AI & Robotics→

New ways to balance cost and reliability in the Gemini API

Google adds Flex and Priority tiers to the Gemini API as AI workloads split in two

Google introduced Flex and Priority service tiers for the Gemini API.
Flex is positioned as a cheaper option for latency-tolerant workloads, with Google citing 50% savings versus Standard.
Priority is aimed at higher-reliability interactive applications using the same synchronous interface.

More in AI & Robotics→