Real-SWE, a new benchmark evaluating frontier AI models on private, real-world enterprise codebases licensed from real companies, was released with Fable 5.1 running in Claude Code posting the top res…
HolaOS released an open-source agentic workspace platform that connects to more than 100 integrations, Model Context Protocol tools, and multiple agent frameworks including Claude Code and Codex. Acco…
ModelRift benchmarked six AI agents, all driven by Claude Opus 5 (1M context) through Claude Code, on three printable-part modeling tasks in CadQuery 2.8.0 and OpenSCAD 2026.06.12, and found all six r…
Developer Jonahss released Concilia Tower, a browser-based WASM rewrite of SimTower built over 6 months with Claude Code, on GitHub and Hacker News. The project replicates the original game's function…
A developer released a Spec Driven Development kit that encodes the rules of the HexaLayered Architecture into a Claude Code-readable .claude directory, including a constitution.md of testable constra…
AI coding assistants such as Claude 3.5 Sonnet and GPT-4o let anyone generate a working prototype in ten minutes, but the barrier to quality is unchanged, according to an analysis echoing Paul Ford's …
A Hacker News user reported that Claude Code now appends a "Claude-Session: https://claude.ai/code/session_xyz" line to git commits by default, even when the older automatic "co-authored by" Claude si…
A developer released AuditAI Scanner, an open-source tool that detects a common authorization flaw in AI-generated code where service-role keys bypass row-level security, letting one tenant read anoth…
A developer spent 30 days testing Claude Code, GitHub Copilot CLI, and Cursor in agent mode across real production projects, finding that agents delivered roughly 4x speedups on boilerplate code with …
A developer guide explains the distinction between agents and skills in Claude Code, describing subagents as isolated worker instances that run a plan-act-observe-repeat loop in their own context wind…
Anthropic said in a 154-page threat report published September 10 that a small freelance team in Russia, tracked as GTG-27005 and calling its project DronDoc or Serafim, used Claude Code to build soft…
A developer built an agent harness that automates the migration of legacy test suites by having an AI agent plan, write, verify, and record evidence for each test without human supervision. The harnes…
Snyk released Agent Scan's Skill Inspector, a free tool that scans AI agent skills and MCP servers for malicious code and security vulnerabilities, after analyzing nearly 4,000 agent skills across maj…
A developer released Agent Team, an open-source MIT-licensed local-first runtime in which a Master agent plans work and Researcher, Builder and Reviewer agents execute it, emitting real artifacts plus…
PonyMux added a read-only Markdown viewer to its Side Panel, letting developers render .md files directly in the terminal via a keyboard shortcut, file:// links, or the `pony open <path>` command. The…
ByteByteGo's system design refresher explains that git revert causes conflicts when a later commit, such as C3, modifies the same lines as the earlier commit being undone, such as C2, because Git cann…
A developer shipped 1,000 production deployments of an AI YouTube analyst called Klyf without ever opening the codebase, driving every migration, deploy, and rollback through Claude Code connected to …
ITerm2 released a Claude Code integration that connects Anthropic's Claude Code CLI to the terminal emulator, displaying each session's state as working, waiting, or idle in the Session Status tool. T…
Anthropic published a 154-page threat intelligence report on September 11, 2026, detailing how freelance Russian developers used its Claude Code AI coding assistant to build autonomous targeting and d…
A developer released ASU (Agent Subscription Usage), an open-source CLI that reads the credentials Claude Code, Codex, and GitHub Copilot already store on disk and queries each provider's usage endpoi…