Webshot.site has launched Model Context Protocol (MCP) support, enabling AI agents like Claude Desktop and Cursor to capture and analyze screenshots directly. The service exposes a single tool that re…
Zvec AI has open-sourced zg (zvec-grep), a local-first search infrastructure that combines vector search with BM25 and ripgrep to enable semantic discovery and relevance ranking for local code and doc…
A developer has released BeatDesign, an open-source, local alternative to Higgsfield Canvas that any MCP-capable agent such as Codex, Claude Code, or Cursor can operate. The tool keeps projects and as…
A developer created Doberman, an open-source tool that intercepts coding agents' tool calls to prevent rogue actions like deleting databases or exfiltrating secrets. It sits on the execution path, iss…
PromptSonar 1.5.1, an execution path analyzer for AI agents and MCP servers, now maps findings to OWASP 2025 Top 10 and ISO/IEC 42001 controls, with a local-first CLI and playground that visualizes so…
Fly.io has launched Sprites, disposable cloud computers designed specifically for running AI agents, with a new MCP server and plugins for Claude Code, Codex, Cursor, Antigravity, opencode, and Grok t…
Olib AI released Web Draw, a free Chrome extension paired with a local MCP server that lets AI agents read and control the browser as structured text instead of screenshots. The tool converts the visi…
A developer building Sirro, a hosted memory layer for AI coding agents served over MCP, shares lessons from production deployment. The project aims to preserve valuable work from coding-agent conversa…
Anthropic released Claude Fable 5.1 and Claude Mythos 5.1, two versions of the same model with different safeguard levels, cutting cache read prices by 75% and improving performance on long-horizon ag…
Val Town, a vibe coding platform, has implemented Dynamic Client Registration (DCR) and Client ID Metadata Documents (CIMD) to enable any app to dynamically authenticate and authorize any other app, s…
Vestige, a local-first memory layer for AI agents, launches as a 25MB Rust binary over MCP that uses causal and temporal links to trace failures back to their root causes, citing research from Nature …
Google for Startups AI Agents Challenge submissions revealed four engineering patterns behind the strongest entries, including bidirectional MCP usage and async event buses. The challenge attracted th…
Anthropic's Model Context Protocol (MCP) is emerging as a universal standard for AI-agent data access, likened to the 'USB-C of AI.' Developers can build one MCP server to connect any MCP-compatible c…
Visual Studio Code 1.137 (Insiders) released on September 2, 2026, adds a feature to display each model's context size as a single token limit instead of separate input and output limits, and improves…
An engineer building the open-source MCP filesystem server octofs has made its shell event-driven after an agent's test suite was cancelled by an idle timeout, causing duplicate runs and false failure…
ToolJet, an internal tools platform, scrapped its multi-agent system built over 11 months and rebuilt around the Model Context Protocol (MCP), letting coding agents like Claude Code and Codex generate…
A growing number of PPC practitioners are managing Google Ads through AI agents using the Model Context Protocol (MCP), which allows AI assistants to read live data and take actions without logging in…
A developer benchmarked file-based AI context anchoring against a hosted memory service, finding the file approach costs roughly 15x less per request due to MCP tool schemas shipping on every request.…
A developer's hands-on test of the Agent2Agent (A2A) protocol across a three-agent commerce flow — checkout, shipping, and claims — shows the protocol's task model is its key value, while payment auth…
CAI Lab released an MCP server for its agentic wallet platform, with configuration instructions for OpenClaw, Hermes, Codex, and Cursor. The server, installed via npm, enables AI agents to perform wal…