A developer has released WeavePort, an open-source plugin runtime for .NET that lets C# applications call capabilities written in Python or TypeScript without rewriting them. The project's Decision Ro…
A developer built master-of, an open-source plugin that gates Claude Code skills behind domain-specific categories so only the skills relevant to a task load into the system prompt. The tool, released…
A developer has launched Nexus API, an open-source personal laboratory project that builds a Node.js API using only native modules such as http, url, fs, crypto, stream, and node:test, deliberately av…
F5 researchers observed roughly 32,000 events in August 2026 targeting .env files and cloud credentials on publicly exposed Vite development servers, including probes for CVE-2026-39364 and older Vite…
A 2026 guide advises operators to distinguish genuine custom machine learning agencies from those that merely wrap foundation model APIs, noting that most pitches involve prompt engineering and workfl…
A developer has released a red-teaming kit that makes LLM safety evaluations reproducible by pinning a versioned probe corpus, raw prompts and replies, and a sha256 hash of the corpus, scoring results…
A developer measured 120 AI-generated code samples from Qwen2.5-Coder 1.5B and found that every case flagged as a swallowed error by a naive detector was either a false positive or a documented fallba…
A developer has published a walkthrough for building a WebMCP tool from scratch, registering a "score_facts" tool directly on a web page via the native document.modelContext API in Chrome or a polyfil…
A security practitioner has published a six-item taxonomy of AI threats, splitting them into four vectors — Shadow AI, Rogue Agent, Prompt Injection, and Model & Data Supply Chain — and two impacts, D…
A developer argues that multi-agent systems fail in production not because of model quality but because their orchestration layers lack the distributed-systems discipline needed for partial tool failu…
Red Hat is developing an open-source MCP server for Kubernetes and OpenShift that lets AI assistants such as VS Code, Copilot, and Cursor read and act on clusters directly. A developer warns that givi…
A developer examines OpenAI's containment infrastructure for evaluating the GPT-6 Astra model after it was flagged as potentially crossing a Critical cybersecurity threshold. The setup relied on air-g…
A developer documented the real boundary between automation and manual work in a self-described 'AI-run' blog, showing that a scheduled PowerShell task and Python script handle posting to Blogger and …
A developer has published a framework for designing human-in-the-loop oversight of AI legal and contract agents, arguing that prevention beats post-hoc review because attorneys cannot realistically ca…
A developer's cost analysis of AI agent runs shows that a 20-turn agent reading roughly 59,000 tokens of material is billed for 656,000 input tokens because stateless model APIs resend the full conver…
A developer published the specification for a validation harness that checks agent configuration kits before release, verifying required files, a sub-300-line CLAUDE.md budget, parseable Cursor frontm…
A developer has released AU Agent Utilities, an open-source MCP server that performs deterministic Australian business-day calculations for AI agents. The server exposes four tools covering business-d…
GreyNoise reported that a threat actor used hundreds of AI agents built on OpenAI's Codex and DeepSeek models to develop and launch exploits against two known PaperCut NG/MF vulnerabilities, compromis…
A developer has released Franca, an open-source Java 21 library published to Maven Central that implements the server side of agent wire protocols, terminating OpenAI Responses and Anthropic Messages …
A developer launched AIMarket Hub, a live public marketplace at modelmarket.dev where AI agents can discover, invoke, and receive signed receipts for third-party capabilities. As of September 15, 2026…