Full-text search across 8103 articles. Combine with topic and date filters; results sorted by relevance.
A developer built Minefield, a Minesweeper mod for Claude Code that opens a game pane beside the transcript while the agent works, shipping with 31 tests run via `claude plugin test` on two pinned Claude Code builds. The…
Paraphern released RugSnare v0.1, an open-source CLI that hash-pins MCP tool descriptions to detect silent post-approval changes, after diffing all 66 release pairs of the official MCP servers and finding 140 silent chan…
HackerRank's fourth Orchestrate hackathon, which concluded September 12, drew 35,700 registrations and 3,062 participants, up from 12,871 registrations and 1,349 participants in the first May edition. HackerRank reported…
Google added Anthropic's Claude Opus 5.5 and Claude Sonnet 5.5 to the model picker in its Antigravity agentic IDE, according to Google's own Antigravity model documentation, with access restricted to paying Google AI Pro…
A developer is building a companion "island" UI for the Ankita desktop AI assistant that surfaces pending approval requests in an always-on-top pill when the main window is hidden, using a 14-pixel wake strip and an Appr…
Uber is running more than 800 Model Context Protocol servers and 5,000 individual tools in production behind a single execution-layer gateway, the company detailed in an October 2026 engineering blog by a team of eight e…
Hedgerow-dev released Rowan, an open-source static application security testing (SAST) scanner for AI and ML projects, installable via `pipx install "rowan-sast[js-crossfile]"` on Python 3.10+. Rowan scans source code an…
Paradigma released Limit 1B Violetto, a 1 billion parameter dense transformer math-specialist model trained from scratch on under 300 billion curated tokens with a 131k context window, under Apache 2.0 weights and a cust…
Microsoft has moved its OpenClaw-based Autopilot agent into expanded private preview inside Microsoft 365, turning Copilot from a prompt-driven chat tool into a standing assignment that checks tasks such as customer rene…
Of eight AI vendors checked on October 3, 2026, six let a team set a cap that stops usage when spend reaches it, while Microsoft's Azure budgets only send alerts and AWS Budgets stops usage only through a budget action t…
Anthropic now lets developers modify Claude Code's behavior and appearance with TypeScript plugins installed via the /plugin command, an announcement that drew 19,861 likes and 4 million views on X. CopilotKit released O…
AgentBadge shipped agent wallets with spending envelopes that enforce rolling per-transaction, daily, weekly, and monthly caps off-chain, denying over-cap payments with an instant 402 spend_cap response before any transa…
A developer published an API guide for converting arbitrary URLs into clean, RAG-ready markdown using AgentSearch Web Extract (agentsearch-web-extract-v1), a paid endpoint that returns headings, paragraphs, lists and lin…
Security researchers at Hacktron disclosed a vulnerability chain in the Electron-based AI assistant Cluely, found in July 2025, that let a malicious page loaded in the app's renderer process silently capture screenshots …
At Supabase Select 2026, Supabase announced that its platform now works code first, letting coding agents set up, change, and check projects through schema and config stored in code. The release includes Declarative Sche…
Backend lead and architect Jawad Ul Hadi built Omni.io, a multi-tenant RAG customer-support engine on NestJS, PostgreSQL with row-level security and pgvector, BullMQ, Gemini and React, designed so that every question sti…
Google announced Gemini 4 Argon, its newest frontier model with a 1-million-token context window built for advanced reasoning and cybersecurity defense, as the headline item in its September 2026 AI roundup. The release …
Arrowproof, an agent skill released by developer ahmtsahin, verifies every box and arrow in an LLM-drawn Excalidraw architecture diagram against a repository's real import graph. In a Flask test, Claude Haiku's diagram y…
TypeSafe AI launched Jev, which it calls the first "System One model," in early access on September 15, 2026, alongside a $40 million seed round led by DCVC. Jev takes text plus typed questions — choice, score, or yes/no…
A developer-authored comparison argues that Claude Code and OpenAI's Codex are effectively tied at the model layer, with the real differences lying in pricing, token consumption, and the programmability of the surroundin…