Full-text search across 8015 articles. Combine with topic and date filters; results sorted by relevance.
A new architectural analysis reveals that production AI agent systems are dominated by operational infrastructure rather than AI decision logic, with Claude Code's leaked source code showing only about 1.6% of its codeba…
The Model Context Protocol (MCP) is an open-source standard built on JSON-RPC 2.0 that unifies how AI agents connect to external systems, eliminating the need for custom integrations for each data source. It follows a th…
Common software bug where a Scoped service (like `OrderService`) caches an entity from a Scoped `DbContext` into a Singleton service (like `IMemoryCache`). This causes data corruption and crashes in production because th…
Anthropic released Claude Haiku 5.5, its first Haiku-tier update in about a year, priced to match OpenAI's GPT-6 Luna and costing roughly 75% less to run than Haiku 4.5 on average, the company said. Anthropic also halved…
TypeSafe's jev-browser-wingman MCP proxy completed all 34 browser-task runs in a 68-run comparison against Playwright alone, which completed 32 of 34 (94%), with both Playwright misses on the file-upload task. The proxy'…
Construct launched an AI agent platform that gives each agent its own cloud computer — with a browser, terminal, file system, schedules, correctable memory and its own email address — starting at $9 a month, undercutting…
Anthropic's Claude Opus 5.5 generates video by writing animation code — self-contained HTML files built on Canvas, SVG, CSS, GSAP, or Three.js that a headless browser renders frame by frame and ffmpeg encodes into MP4. A…
GitGuardian has published a Docker Sandbox Mixin Kit that automatically installs its ggshield tool and enables AI hooks, giving developers a controlled way to run autonomous coding assistants. The kit pairs Docker Sandbo…
Google's free Antigravity tier exhausted its weekly quota on every model it serves — Gemini 3.8 Flash, Claude Opus 4.6 and GPT-OSS — in a single afternoon of testing, with each pool reporting "Individual quota reached" a…
Claude Code 2.1.277 began reading AGENTS.md on 18 September 2026, making five of the six major coding agents read that file without setup, though Claude Code still loads skills only from .claude/skills/ and not the share…
A developer released smcp v1.0.1, a shared-skills and MCP stack that packages reusable agent skills, including one for driving the Appwrite CLI. The Appwrite skill documents installation, login, project initialization, m…
A developer writing as 晚安code on Juejin published a version-aware walkthrough of building a minimal MCP server with Python's FastMCP, showing how type annotations and docstrings generate the JSON Schema and tool descript…
Sifthound, an open-source self-hosted web search API for AI agents, launched as a drop-in replacement for the Tavily API, serving the same /search, /extract, /crawl and /map endpoints so existing Tavily code works by cha…
Claude Code reads AGENTS.md only when no CLAUDE.md, .claude/CLAUDE.md or CLAUDE.local.md exists in the working directory or any parent directory, and until version 2.1.281 the loader was gated behind the remote feature f…
Cline shipped Cline Desktop this week, a standalone open-source coding agent app for macOS (generally available) and Windows (beta) that runs without an IDE and supports parallel agent sessions, cron-style job scheduling…
A developer built Spud, a local-first push-to-talk dictation tool, by pairing with Gemini 3.8 Flash through Google's agy CLI, integrating it with the Hyprland Wayland compositor on Arch-based EndeavourOS. The setup lets …
GitHub Copilot reads `.github/copilot-instructions.md` on every request in a repository, but the file should stay under two pages and avoid task-specific rules, according to GitHub's custom instructions documentation che…
A developer outlined a staged approach to running Google's Gemma 4 locally, starting with CPU-only text inference in llama.cpp using a Q4 quantized checkpoint and the --no-mmproj flag before adding GPU offload and vision…
The Georgian AI Lab outlined a resource-efficiency framework for agentic development that treats model selection as an ongoing cycle of capability investment and cost optimization, arguing open-weight models should absor…
Croft published a September 18, 2026 guide by Rich Chetwynd on hosting a Claude-built financial model as a private team app, letting colleagues open a shared URL and work against shared saved numbers instead of emailed .…