A new biomedical agent system called BioManus uses graph-based planning over standardized tool interfaces to overcome bottlenecks in current prompt-based approaches. Developed by researchers, BioManus…
Jack Kao, developer of the MCP-native QA toolkit mk-qa-master, demonstrated a new edge AI testing capability by pointing a YOLOv8 object detection model at his laptop webcam through an RTSP stream. Th…
Pie, a new open-source terminal-based AI coding agent written in Rust, has been released as a rewrite of the original pi project. The agent runs inside a project directory, can inspect and edit files,…
Snyk advises organizations to shift AI security budgets from fragmented tool spending to unified investments in visibility, governance, and control across the full AI lifecycle. The company warns that…
DNS-AID, a new protocol and reference implementation, enables AI agents to discover and verify each other using the existing Domain Name System (DNS) infrastructure instead of centralized registries o…
A designer-turned-developer has launched Scrape Agent, a pay-per-use web scraping API built with Claude's assistance that charges $0.01 USDC per call via the x402 micropayment protocol. The API extrac…
Visr, a new open-source tool, transcribes the entire trajectory of terminal sessions—including every command, output, retry, and fix—rather than just the final diff. The tool, installable via Homebrew…
A developer has identified a new class of supply-chain attack called the "MCP rug pull," where malicious Model Context Protocol (MCP) servers dynamically change their tool surfaces between sessions wh…
A new framework outlines five levels for integrating AI into existing SaaS applications, ranging from basic API access via MCP servers to full conversational interfaces with history and tool states. T…
A developer who built an MCP server for QRflows submitted it to Anthropic's official Connector Directory and documented the process. The submission form requires server basics, connection details, too…
A developer benchmarked A2A (Agent2Agent) protocol agents across Google Cloud, Azure, and AWS by deploying Rust-based agents using the Antigravity CLI. The cross-cloud test measured native language ex…
TabularisDB released v0.13.0, adding Kubernetes port-forward tunnels as a first-class transport option, a Quick Navigator for schema browsing via Cmd+P, and MCP support for plugin-driven connections. …
A developer built an MCP server called Scribefy that gives AI assistants like Claude direct access to YouTube tools, eliminating the need to manually copy and paste transcripts. The tool provides four…
A developer has built TriggerApp, a tool that enables complex Google Apps Script scheduling through a declarative JSON engine, bypassing the platform's native limitations that restrict users to basic …
Google researchers have developed the A2A (Agent-to-Agent) Protocol, a standard for enabling autonomous AI agents to discover and delegate tasks to one another. The protocol allows agents to publish m…
Agent Threat Rules (ATR), an open detection format for AI agent security threats, has been released to address vulnerabilities such as prompt injection, tool poisoning, and credential theft in coding …
A developer created Klavex, a CLI tool that eliminates plaintext `.env` files by storing secrets in an encrypted vault and injecting them only into child processes. The tool prevents coding agents lik…
Lightpanda, a headless browser without graphical rendering, outperformed Chrome in speed and cost when benchmarked on text-based AI agent tasks using AssistantBench and GAIA Level 1, with the tool sur…
Railway has launched a new "Agent Experience" that allows developers to deploy and manage full-stack applications entirely from the command line using AI agents, eliminating the need for dashboards. T…
Agent systems suffer from a subtle bug where the agent's timeout budget and the tool's timeout budget start from different events, causing tools that complete within their own timeout to be prematurel…