A developer released mcp-bastion, an open-source proxy that addresses reliability and security gaps in the Model Context Protocol (MCP). The proxy handles MCP server disconnections by providing status…
Entire, the developer-platform startup founded by former GitHub CEO Thomas Dohmke, launched a preview of a distributed Git network designed to handle the heavy read traffic from AI coding agents. The …
BESSER released an open-source UML drawing skill for AI coding agents that generates structurally validated class diagrams as rendered images from natural language descriptions or existing source code…
Enterprises evaluating AI coding agents should measure ROI beyond code generation volume, focusing on software delivery speed, quality, and business outcomes. Metrics like lead time for changes, cycle…
GitHub's preview Agentic Workflows are vulnerable to a prompt injection attack that can leak private repository contents, according to Noma Security. An unauthenticated attacker can embed hidden instr…
On July 7, Noma Security disclosed a critical prompt injection flaw in GitHub's Agentic Workflows, dubbed GitLost, that allows any free GitHub account to extract private repository contents by posting…
Claire Vo built a custom AI harness for bug triage at ChatPRD using the Claude Agent SDK, a terminal UI with Ink, and adapters for Sentry, Linear, GitHub, and Vercel. The harness automates evidence ga…
Security firm Noma Labs discovered a prompt injection vulnerability, named GitLost, in GitHub's Agentic Workflows that allows attackers to trick the AI agent into leaking private repository contents i…
Developer Brad Bonanno created an open-source skill called /watch that enables Claude AI to analyze YouTube videos by slicing them into frames and audio, overcoming the AI's inability to process video…
A second-year Computer Engineering student built Aigris, an experimental on-device AI cybersecurity agent for Android that detects phishing, malicious links, and social engineering attacks while prese…
A developer released rubric-bench v0.1, a TypeScript library and CLI that treats LLM judges as code under test by running regression tests against a golden set of cases. The tool, which scored 95.8% o…
Anthropic's decision to block flat-rate subscriptions from powering AI agents has caused API costs to skyrocket, leaving developers facing five-digit bills. A comparison of n8n and OpenClaw reveals th…
Scalekit ran 75 benchmark runs comparing CLI and MCP agents on identical GitHub tasks, finding CLI was 10 to 32x cheaper and 100% reliable, while MCP hit only 72% reliability. Perplexity's CTO reporte…
Syncless, a new tool for AI agents, aims to reduce collaboration friction by synchronizing context across team members through automated workflows called Collaboration Templates, cutting over 80% of t…
Software-engineering interviews are shifting from memorized coding tests toward AI fluency and project reasoning, with companies like Dropbox and Cisco now allowing AI tools during assessments and rec…
Noma Labs disclosed GitLost, a vulnerability in GitHub Agentic Workflows that allowed an attacker to exfiltrate private repository contents via a crafted public issue. The attack exploited the AI agen…
GitHub Mobile now lets users fix pull request merge conflicts using Copilot cloud agent directly from the mobile app. The feature allows developers to tap 'Fix with Copilot' to generate a prefilled pr…
GitHub Mobile now supports live notifications for remote Copilot CLI sessions, allowing users to track progress, receive input requests, and jump back into sessions via iOS live activities or Android …
A developer built Meeting Presenter, an AI skill that joins video calls, shares a screen, and presents slide decks autonomously. The tool can generate slides from rough notes or a single sentence, and…
Comcent Community Edition, an open-source self-hosted voice infrastructure platform, was released on GitHub after two years of development. The platform provides SIP voice infrastructure, AI-powered c…