A developer released skill-extractor, an open-source tool that mines coding agent transcripts to generate reusable skills, scoring candidates by confidence and utility while redacting secrets and requ…
Arbor v2.4.0, a code graph MCP server, was released in July 2026 with support for the MCP 2026-07-28 protocol, Tasks extension, MCP Apps for interactive UI, and Streamable HTTP transport. The update e…
AppSignal launched an MCP server that lets developers query monitoring data using plain language inside editors like VS Code and Cursor. The server exposes tools for errors, incidents, anomalies, metr…
AI Avatar, a free app that animates VRoid 3D avatars in response to AI chat and keyboard input in VS Code and Chrome, released version 15 with major updates. The update includes new visual effects cre…
CodeTalk, a new developer tool, recovers the rationale behind AI-written code by grounding explanations in real git commit history and session transcripts, using zero-LLM deterministic lookup. The too…
Newer AI models with cheaper per-token pricing can lead to higher costs and worse output, according to tests comparing Claude Sonnet 4.6 and Sonnet 5 on 150 agent tasks. Sonnet 5 consumed up to 12x mo…
LLM code generation enthusiasts are creating 'vibe forks'—reimplementations of existing projects using AI coding tools—raising concerns about the value of source code as a moat. However, curation, tru…
Apify released CLI version 1.7.0 with improvements for AI coding agents, including clearer guidance for `apify call`, explicit final-status summaries for builds and runs, a new `apify mcp install` com…
Banks are rapidly adopting agentic AI systems that can take actions, not just answer questions, creating a new security risk of overprivileged agents. In April 2026, Five Eyes cyber agencies issued jo…
SneakRead, an open-source browser tool, disguises any article as professional applications like VS Code, Excel, or Slack to help users read the web discreetly at work. It offers 14 disguises, a boss k…
A developer built Decispher, a tool that captures engineering context from platforms like Slack, Jira, and GitHub to feed AI agents, reducing token usage by 35-65% and improving code consistency acros…
GitHub Copilot Vision went generally available on July 1, 2026, allowing all Copilot subscribers to attach images and PDFs to chat prompts for visual reasoning alongside code. The feature is uneven ac…
Tencent released the General Availability version of its Hy3 AI model, now free for a limited time on the Kilo platform. The 295B-parameter Mixture-of-Experts model features improved reasoning, reduce…
Microsoft and OpenAI partnered to tune the GPT-5.5 system prompt in VS Code, testing two variants that nudge the agent to explore less and validate sooner. The experiment, run over two weeks on live t…
GitHub Copilot's shift to usage-based billing on June 1, 2026, has made token efficiency a direct expense for developers. Microsoft and GitHub have introduced extended prompt caching and deferred tool…
Google Cloud launched the Workbench Notebooks extension for VS Code, enabling data scientists to manage cloud-based Jupyter environments directly from their local IDE. The open-source tool aims to str…
GitHub Copilot has added Kimi K2.7 Code, an open-weight model from Chinese AI startup Moonshot AI, as a selectable option in its model picker for the first time. Hosted on Microsoft Azure and billed b…
GitHub announced that enterprise administrators can now set Copilot to auto model selection by default for new conversations via the managed-settings.json file. The setting applies to users licensed t…
A developer built SafeMCP to address security concerns with the Model Context Protocol, which allows AI agents to access filesystems. The tool aims to prevent AI agents from performing unsafe file ope…
OpenAI announced its first hardware product, the Codex Micro, a programmable macro pad built with Work Louder, launching July 15. The device targets power users of OpenAI's Codex platform, which has f…