A developer built Textokit, an autonomous agent-run store that exposes HTTP services and accepts per-call USDC payments on Base via the x402 protocol, handling payment challenges, facilitator verifica…
A developer published a consultation kit showing how to use a Claude Code PreToolUse hook with a Bash matcher to run a Python guard script that inspects proposed shell commands and blocks recursive de…
A developer documented building a Stripe direct-charges payment module for a WordPress/Dokan multi-vendor marketplace using agentic AI coding tools, logging each step with timestamps. AI agents produc…
A developer published yangshun2005/superpowers-cn, a Chinese translation of obra/superpowers, a 307,936-star MIT-licensed agent skills framework that forces coding agents to pause, gather requirements…
A developer built BengaliStoryTeller, a free, fully offline text-to-speech tool that reads Bengali bedtime stories aloud sentence by sentence on a CPU-only Ubuntu laptop, inserting natural pauses at t…
A developer behind LiveFaceSwap AI outlined a troubleshooting guide for Halloween face-swap failures, noting that a working browser webcam preview does not mean the processed image is available as a v…
A developer has published a reference architecture for securing AI coding agents by wrapping them in a four-layer harness that combines OS-level sandboxing, policy-as-code enforcement via OPA/CEL, con…
A roundup of late-October 2026 LLM evaluation research finds that single benchmark numbers and LLM-judge verdicts are far less reliable than the dashboards built on them suggest. Among the cited work,…
A developer detailed how an AI phone agent can book appointments directly into GoHighLevel using three public API calls: upserting the contact, fetching free slots for a calendar, and creating the app…
A developer implemented and benchmarked Wake-Sleep Null-Space Consolidation (WS-NSC), a continual-learning method that projects LoRA weight updates onto the orthogonal null-space of prior activations,…
A developer documented how Claude Code's structured output mode forces subagents to return schema-validated JSON instead of prose, using Zod schemas converted to JSON Schema and passed as an outputFor…
A two-person team at OxHack '26 in Oxford built Smart Connect, an AI agent system that places real phone calls to businesses on a user's behalf, using Gemini function calling to plan calls, ElevenLabs…
Agentic AI architect Omkar Vijay Ghate described building multilingual Hindi-English voice agents for Indian businesses, including a Hinglish lead-qualification agent for TVS Motors that qualified 40%…
A developer built PhantomOps, an open-source "FinOps & kernel agent" that runs entirely offline to detect zombie and runaway processes on Windows and cloud-cost anomalies, using a local TabPFN classif…
The team behind veilvex.com, a four-language Astro static site, generates its llms.txt and robots.txt files at build time from the same i18n content files that render the pages, so prices and descript…
As of 2 August 2026, the EU AI Act's Article 50 transparency obligations are in force, requiring disclosure that users are interacting with AI, machine-readable marking of synthetic content, and speci…
Shopify opened its checkout to browser-based AI agents and launched an MCP endpoint (mcp.shop.com) that lets any MCP-compatible agent search its catalog of more than 1 billion products, build carts an…
A Speakeasy growth engineer outlined a framework for "agent compliance," arguing that proving AI agents stay within required controls depends on runtime records capturing both what an agent saw and pr…
A developer contributed a series of upstream merge requests to GitLab and the GitLab Language Server (gitlab-lsp), extending GitLab's Model Context Protocol (MCP) tooling that connects AI agents and I…
Security researchers at NorForge discovered roughly two dozen exposed control panels for Cairn, an open-source AI penetration-testing tool, being used maliciously by a criminal group they designate AI…