Latest news with #VSCode
&w=3840&q=100)
Business Standard
26-05-2025
- Business
- Business Standard
PayU rolls out MCP server to integrate AI assistants, payment systems
Prosus-backed fintech PayU has joined other peers in the category to roll out a Model Context Protocol (MCP) server, where its merchants can connect their artificial intelligence (AI) assistants to the company's payment systems. Razorpay and Cashfree Payments rolled out the offering for their customers earlier this month. An MCP server acts as a bridge to communicate between AI assistants — such as Claude or VS Code — and the company's payment gateway. Think of it like a 'universal connector' — in other words, like a USB-C port — that allows different software systems to work together easily. This enables AI agents and assistants to interface directly with core application programming interfaces (APIs), streamlining integration for merchants of all sizes. PayU said early use cases include generating payment links, emailing invoices to customers, fetching payment status using invoice IDs, and checking transaction or refund statuses. The company said it was expanding the MCP server's capabilities to include the ability to create invoices and orders through AI assistants and to onboard customers efficiently. 'The future of payments lies in intelligent automation and seamless integrations with advanced tools including GenAI platforms. With our latest MCP server, we are taking a leap forward in payments technology, enabling businesses to make their financial operations simple, more efficient, all while ensuring the highest standards of security,' said Narendra Babu, Chief Technology Officer at PayU.
Techday NZ
20-05-2025
- Business
- Techday NZ
GitHub debuts Copilot agent to boost coding with secure oversight
GitHub has announced that its Copilot software now includes an asynchronous coding agent, directly integrated into GitHub and accessible from Visual Studio Code (VS Code). The new Copilot coding agent operates within GitHub's native control layer and is powered by GitHub Actions, enabling developers to delegate both routine and specialised coding tasks. It is designed to require human approval before any continuous integration or continuous deployment (CI/CD) workflows proceed, ensuring that developers retain oversight of code changes. The coding agent, previously referred to as Project Padawan, is intended to help developers work more quickly and at greater scale, while supporting secure code commitments. The Copilot coding agent is now available to all Copilot Enterprise and Copilot Pro+ users, with organisations including CommBank, Carvana, and EY among those already recognising its usage. GitHub Chief Executive Officer Thomas Dohmke said, "GitHub is where the world's developers work on their projects. Now, it's becoming the place where they collaborate with agents in a configurable, steerable, and verifiable way. It's vital that organisations and developers are ready to embrace these agents without compromising their security posture." He added, "Built around an integrated, secure, and fully customisable development environment powered by GitHub Actions, the Copilot coding agent is the most enterprise-ready of its kind—amplifying human developers with trust by design. And these protections aren't just for us: as the new home of AI agents, we're making the same primitives available to partners to ensure an open ecosystem for agentic peer programming." The Copilot coding agent integrates with the software development life cycle. Developers can activate the agent by assigning a GitHub issue or initiating a session through Copilot Chat in VS Code. Commits generated by the agent are pushed to a draft pull request and can be tracked through session logs. Developers can review the agent's work, provide feedback, and request further iterations via regular pull request reviews. The agent is designed to maintain security through features such as branch protections and managed internet access. Additionally, any pull requests created by the agent require manual approval before triggering any CI/CD activities, establishing an additional layer of control over build and deployment processes. With the Model Context Protocol (MCP), developers are able to provide the agent with access to external data and additional capabilities. Configuration of MCP servers is available within repository settings, offering flexibility in how the agent interacts with software and data. The Copilot coding agent's computing environment is underpinned by GitHub Actions, leveraging a platform with more than 25,000 actions available in the GitHub Marketplace. Every weekday, over 40 million tasks are handled by GitHub-hosted and self-hosted runners. The agent thus operates within an established infrastructure that supports a broad range of development workflows at both open source and large enterprise scale. During private preview testing, the agent demonstrated effectiveness at completing low-to-medium complexity tasks in established codebases. These tasks include adding features, resolving bugs, extending tests, refactoring code, and improving documentation. Rodrigo Castillo, Chief Technology Officer at CommBank, commented, "We believe agentic AI is the next phase of evolution for software engineering. Together with GitHub, we have tightened DevSecOps cycles, while using existing security controls without modification. We're also automating common tasks, such as tech debt management, giving our engineering teams more time for creative flow: designing better products and experiences for our customers, and better platforms for our other engineers." Alex Devkar, Senior Vice President, Engineering and Analytics at Carvana, said, "The GitHub Copilot coding agent fits into our existing workflow and converts specifications to production code in minutes. This increases our velocity and enables our team to channel their energy toward higher-level creative work." James Zabinski, DevEx Lead at EY, added, "The Copilot coding agent is opening up doors for human developers to have their own agent-driven team, all working in parallel to amplify their work. We're now able to assign tasks that would typically detract from deeper, more complex work—allowing developers to focus on high-value coding tasks." Copilot Enterprise and Copilot Pro+ users can access the agent via consumption of Copilot premium requests and GitHub Actions minutes, both of which are included as part of their subscription entitlements. Kate Holterhoff, senior analyst at RedMonk, observed, "With its autonomous coding agent, GitHub is looking to shift Copilot from an in-editor assistant to a genuine collaborator in the development process. This evolution aims to enable teams to delegate implementation tasks and thereby achieve a more efficient allocation of developer resources across the software lifecycle." GitHub has also announced new artificial intelligence-related features intended to increase flexibility for software developers. Next month, GitHub will begin open sourcing the Copilot Chat extension for VS Code under the MIT licence, allowing developers to inspect and extend the AI's functionality. Over time, key AI features will be integrated directly into the VS Code core to further support developer control and transparency. All GitHub users now have access to the Models tab within repositories, where they can build, test, and manage AI features. This update includes support for prompt management, lightweight evaluations, and enterprise controls for secure and governed AI usage on the platform. GitHub Models has expanded to include support for Grok 3 from xAI, broadening the choice of models available to developers seeking different AI capabilities in their projects. Agent mode functionality is being extended with availability in JetBrains, Eclipse, and Xcode integrated development environments, allowing Copilot users to work with agents in a wider range of programming tools.
Yahoo
19-05-2025
- Yahoo
Microsoft open-sources a command-line text editor and more at Build
At its Build 2025 conference, Microsoft open-sourced a number of apps and tools, including a new command-line text editor for Windows called Edit. Open source software may not earn the company direct revenue, but it can serve as a form of market research — and a funnel to paid applications and services. By contributing to the open-source community, Microsoft gains valuable knowledge and product suggestions, as well as ideas for future directions. Edit, which will be installed by default on Windows via the Windows Insider Program beginning this summer, will allow developers to edit files directly in the command line by running the command "edit." The goal is to minimize unnecessary context switching and let developers stay in their current flows, says Microsoft. Elsewhere, Microsoft is open-sourcing GitHub Copilot in VS Code, its assistive coding extension for Visual Studio Code. Over the next few months, AI-powered capabilities from the GitHub Copilot extension will migrate to the VS Code open-source repository, says Microsoft. Lastly, Windows Subsystem for Linux (WSL), the feature in Windows that allows users to run a Linux environment directly on their Windows system, will be open-sourced, says Microsoft. This will allow developers to access the source code and make any changes they may need for a particular use case. This article originally appeared on TechCrunch at Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Yahoo
19-05-2025
- Yahoo
Microsoft open-sources a command-line text editor and more at Build
At its Build 2025 conference, Microsoft open-sourced a number of apps and tools, including a new command-line text editor for Windows called Edit. Open source software may not earn the company direct revenue, but it can serve as a form of market research — and a funnel to paid applications and services. By contributing to the open-source community, Microsoft gains valuable knowledge and product suggestions, as well as ideas for future directions. Edit, which will be installed by default on Windows via the Windows Insider Program beginning this summer, will allow developers to edit files directly in the command line by running the command "edit." The goal is to minimize unnecessary context switching and let developers stay in their current flows, says Microsoft. Elsewhere, Microsoft is open-sourcing GitHub Copilot in VS Code, its assistive coding extension for Visual Studio Code. Over the next few months, AI-powered capabilities from the GitHub Copilot extension will migrate to the VS Code open-source repository, says Microsoft. Lastly, Windows Subsystem for Linux (WSL), the feature in Windows that allows users to run a Linux environment directly on their Windows system, will be open-sourced, says Microsoft. This will allow developers to access the source code and make any changes they may need for a particular use case.
Yahoo
09-05-2025
- Business
- Yahoo
Zencoder Launches Zen Agents: Industry-First Platform for Organization-Wide Custom Agents and Open-Source Marketplace
Breakthrough Technology Empowers Development Teams to Create, Share, and Leverage Specialized AI Tools That Accelerate Software Delivery SILICON VALLEY, Calif., May 9, 2025 /PRNewswire/ -- Today, Zencoder announces the launch of Zen Agents, delivering two groundbreaking innovations that transform AI-assisted development: a platform enabling teams to create and share custom agents organization-wide, and an open-source marketplace for community-contributed agents. This breakthrough significantly expands Zencoder's ability to empower professional developers to ship better software faster through its deep integration with VS Code, JetBrains, and other industry-standard tools. Custom Agents with Organization-Wide Sharing Zen Agents solve real development challenges by letting teams: Eliminate redundant coding tasks: Create specialized agents with tailored instructions and toolsets for specific frameworks, codebases, or workflows. Standardize development practices: Admin-created agents can be deployed to every team member, ensuring consistent practices and standards Reduce Context-Switching Cost: Connect seamlessly to tools through native integrations & MCP to maintain developer focus. "Zen Agents create the perfect harmony between human creativity and targeted AI assistance," said Andrew Filev, CEO and Founder of Zencoder. "By enabling teams to craft agents with specific expertise and then deploy them organization-wide, we're helping developers achieve that elusive technical flow state where complex problems seem to solve themselves." Matt Walker, Co-founder and CTO of Simon Data, shares the real-world impact: "Zen Agents unlocked the next level of productivity for our teams. Through MCP integration with our Jira, Confluence, and GitHub tools, our custom agents automate not just coding but project management and documentation tasks as well. By sharing these specialized agents across teams, we've eliminated hours of context-switching and created an organization that benefits from our collective expertise. Zencoder delivers what modern engineering teams truly need – AI that understands our entire development ecosystem." Open-Source Agent Marketplace Complementing the organization-wide functionality, Zencoder introduces an industry-first open-source marketplace for AI agents: Community-Driven Library: A public GitHub repository under MIT License where developers can discover and share agent configurations Transparent Submissions: Streamlined process for contributing custom agents via pull requests, with expert review by Zencoder Web-Based Discovery Portal: Dedicated section on the Zencoder website for browsing the expanding agent ecosystem Unlike other AI coding platforms that limit sharing capabilities, ZenAgents creates a truly open ecosystem where teams can publish their specialized agents to the marketplace or discover ready-made agents from other contributors. This collaborative approach exponentially multiplies the value of custom agents while fostering a community that builds on collective expertise. "Our mission goes beyond building products—we're fostering a community where engineering knowledge multiplies," noted Filev. "The open-source marketplace means everyone benefits from specialized expertise, whether you're building microservices, working with machine learning pipelines, or optimizing legacy code." Use Cases That Deliver Measurable Results Zen Agents deliver concrete value for development teams through specialized AI assistants including: Framework Experts: Agents that deeply understand React, Django, Spring, or other frameworks, instantly recalling best practices and common patterns Testing Specialists: Focused agents that generate comprehensive test suites aligned with organization-specific testing approaches Refactoring Architects: Specialized tools that implement organization-specific refactoring patterns and practices Documentation Craftsmen: Agents that create standardized, high-quality documentation that follows team conventions These specialized agents leverage Zencoder's industry-leading integration capabilities: Visual MCP Tool Configuration: Intuitive interface for creating custom Model Context Protocol connections Pre-vetted Tool Library: Curated collection of productivity-enhancing MCP servers, including support for select third-party registries. End-to-End Pipeline Support: Connect agents to your entire development workflow with 20+ DevOps integrations Availability & Resources Zen Agents are available now as part of Zencoder's platform. For more information or to start a free trial, visit The Zen Agents open-source marketplace is accessible at under an MIT license, with initial contributions from Zencoder and a growing community of developers. Browse available agents and learn more about contributing at About Zencoder Zencoder, headquartered in Silicon Valley, delivers AI coding and testing agents that integrate directly into developers' existing workflows. Founded by Andrew Filev and driven by a global team of 50+ experienced engineers, Zencoder combines deep code understanding (Repo Grokking™) with iterative AI approaches (Agentic Repair) to help organizations ship impactful software products faster. Zencoder holds ISO 27001, SOC 2 Type II certification as well as ISO 42001 for responsible AI management systems. Media Contact Ignacio Ramirez, Founder @ Switch PR, email: ignacio@ Phone: 415-517-6708 All product and company names herein may be trademarks of their respective owners. Zencoder is not affiliated with or endorsed by GitHub. View original content to download multimedia: SOURCE Zencoder
