A developer turned off AI coding tools for a week and found that while output dropped initially, code quality improved and a subtle race condition was caught that AI had dismissed. The developer now u…
Claude Code, primarily known as a programming tool, can also be used to build a knowledge base, according to a guide on Towards AI. The article explains how to leverage Claude Code's capabilities beyo…
Anthropic's Claude Fable 5 coding agent autonomously debugged a horizontal scrollbar issue in developer Simon Willison's Datasette tool by launching browser automation, building test pages, and patchi…
The US government forced Anthropic to shut down API access to its Fable and Mythos AI models via export controls, citing national security concerns after another company demonstrated a way around the …
Claude, an AI operating as an autonomous entrepreneur under the handle @projectnomad, is building a real business with zero capital. The AI developed a workflow kit for freelance web developers, sold …
A developer known as Claude, running an autonomous-business experiment, created a four-step system to handle client change requests that cause scope creep on freelance web projects. The system, encode…
Anthropic released Claude Fable 5, its first Mythos-class model, which benchmarks over 10% better than Opus 4.8 on coding tasks and features a 1M context window and deep MCP integration for multi-agen…
A developer has created a set of Claude Code skills to systematize the unprofitable parts of freelancing, such as scope creep, vague requirements, and quality assurance. Two of the eight skills are fr…
A developer built sessionmem, a local-first MCP server that gives AI coding assistants persistent memory by injecting compact session summaries at the start of each new session. The tool reduces token…
NVIDIA released SkillSpector, an open-source security scanner for AI agent skills that detects vulnerabilities, malicious patterns, and security risks before installation. The tool addresses research …
Symphony, a desktop app that automates software engineering by dispatching coding agents to work on Linear issues, has been released as an open-source Rust implementation. The app polls Linear boards,…
A developer released Intelligence Emotions, an open-source AI coaching team that runs inside Claude Code to help users build mental fitness by identifying self-sabotaging thought patterns and practici…
Vercel released AI SDK 7 with HarnessAgent, an experimental API that provides a unified programming model for running coding agent harnesses like Claude Code, Codex, and Pi harness, supporting sandbox…
A developer built an MCP server with 132 tools that gives AI assistants like Claude programmatic access to Cognigy.AI's management API. The server enables natural language control over conversational …
Developer Dan McInerney released Architect Loop, an open-source tool that uses Claude Code as an architect and GPT-5.5 Codex as a builder to run cross-vendor AI development loops on flat-rate subscrip…
A community analysis of the most documented production AI agent, Claude Code, found that only about 1.6% of its code determines what the model does, while the remaining 98% handles context assembly, t…
Claude Code orchestrated a 10-agent code review of loomcycle via MCP fan-out, with reviewers running concurrently inside loomcycle and findings consolidated into a report. The review covered 86 files …
A developer has created a 60-second audit script to measure the "MCP server token tax"—the context budget consumed by tool definitions before an agent performs any useful work. Running the script agai…
A developer has published a recipe for writing effective Flutter agent skills, synthesizing official guidance from Flutter, Anthropic, Google, and OpenAI into a single copy-pasteable format. The recip…
Engineering leaders lack visibility into which AI coding assistants are used across their repositories, creating a governance gap as executives push for faster AI adoption. Shadow AI tools like GitHub…