Full-text search across 68688 articles. Combine with topic and date filters; results sorted by relevance.
Datawebot launched a hosted MCP server that supplies AI agents with live ecommerce product data, letting any MCP client such as Claude, ChatGPT, Cursor, VS Code or Gemini CLI query current listings across shops without a…
MLflow 3.9 shipped on October 6 with MemAlign, a judge-calibration algorithm that MLflow reports cuts LLM-as-a-judge errors by 74–89% across commonly misaligned evaluation dimensions and improves overall agreement with h…
A developer built Dogear, an open-source app that photographs highlighted pages in paper books and, in a nightly batch job, extracts the highlighted passages using a small open-weight model (Gemma 4 e4b via Ollama) plus …
A developer built agent-usage-guard, a Claude Code mod that adds machine-wide admission control to autonomous agent sessions after a single research prompt spawned 394 subagent calls, 341 running concurrently, pushing 84…
An X user in May 2026 tricked xAI's Grok trading bot companion Bankrbot into transferring 3 billion DRB tokens worth roughly $200,000 to an unintended wallet on the Base network by sending a Bankr Club membership NFT con…
A developer built MediaMend, an open-source local AI assistant that scans folders for blurry photos, blank video frames, silent recordings, empty files and duplicates, then routes flagged items through a review queue and…
CERT-In, India's national cybersecurity agency under MeitY, established a Cyber Defence Centre in May 2026 that uses open-weight AI models and open-source tools to continuously scan critical government ministry websites …
A developer evaluated Callstack's open-source agent-device tool, which lets an AI agent drive iOS and Android apps and inspect the screen, for testing a Flutter app after Google's Android-only Artemis fell short on iOS s…
Farol, an open-source workspace for AI coding agents, runs pipelines of shell and AI steps against an agent's branch and sends any failed step's report back to the agent to fix, looping until every step passes. The tool …
OpenAI's GPT-5.6 Sol, working under the company's "Patch the Planet" vulnerability research program, discovered two unauthenticated remote-code-execution flaws in PHP tracked as CVE-2026-109618 and CVE-2026-109619 and ni…
A developer built User-Friendly Forces, a Chrome extension that analyzes website privacy policies and returns a 0–100 privacy score, a plain-English three-sentence summary, and color-coded red flags. The tool runs infere…
Developer Naman Soni released Infinite, a C++20 audio and 3D visual engine exposed through the Model Context Protocol and a Python SDK, letting AI coding assistants like Claude Desktop, Cursor and Devin generate music, s…
A developer built EchoDeck, an open-source voice-first flashcard coach that generates cards from notes and grades spoken answers, adding a fully local mode for the Hacktoberfest Open-Source AI Challenge. The local mode r…
A new practitioner guide argues that standard package-lock.json files are necessary but incomplete for AI agents, because agents also depend on models, prompts, MCP tool servers, policy bundles and retrieval configuratio…
An experimental open-source project, piazzetta-433-esphome by MaximeHTL, lets Home Assistant control a Piazzetta pellet stove by emulating its F0203-1480V3 433.92 MHz OOK radio remote, using an ESP32 and an SX1278-based …
Kirikae, a Rust-based static recompiler that lifts Nintendo Switch ARM64 executables into native Windows and Linux programs via the Cranelift backend, is in an early preview state that can run complete commercial games b…
Moonshot AI released Kimi K3.1 Pro, a post-trained iteration of its Kimi K3 model built on a reported 2.8-trillion-parameter Mixture-of-Experts design that activates roughly 104 billion parameters per token and supports …
Role engineering — delegating goals, context and examples to AI agents the way a manager onboards a new employee — is replacing prompt engineering as models grow capable of working from rough goals, according to guidance…
A developer running AI agents unattended in production described a five-layer operational safety stack for preventing destructive agent actions, arguing that prompt instructions like "be careful with deletions" cannot su…
A developer built Hermes Micro-Agent, a single HTTP endpoint that accepts USDC payments on the Base network and returns task results such as summarization, translation, code review and image description without requiring…