Full-text search across 60195 articles. Combine with topic and date filters; results sorted by relevance.
A team led by coder Sword ported the PCSX2 PlayStation 2 emulator to a jailbroken PlayStation 5 using Anthropic's Claude AI, enabling the console to recognize and play physical PS2 game discs. Only 108 games have been te…
SWE-Duel, a self-scaling coding-agent arena introduced in arXiv paper 2610.12569v1, ran a 1,500-turn tournament among 11 model-harness participants on 15 repositories in five languages, with GPT-5.5 on Codex CLI ranking …
Bold Software released Shelley, an open-source, self-modifying coding agent that runs as a web page and installs via `brew install --cask boldsoftware/tap/shelley`. Shelley runs multiple concurrent conversations, each wi…
A developer built Mind Palace, a Windows desktop memory app that captures coding sessions even when its Angular/Tauri interface is closed, using approved Codex hooks that invoke a small local receiver writing atomic spoo…
Vercel's CLI now lets AI coding agents handle domain discovery, availability checks and pricing, but blocks the actual purchase: in a non-interactive session, `vercel domains buy` returns a structured, machine-readable e…
A second-generation Spanish family business servicing and repairing car-wash equipment has built its own ERP in production and a set of AI agents on Claude Code and an MCP server, despite having no programmers on staff. …
A developer published a short shell script that scans the bundled Claude Code binaries on macOS for embedded .gov domain strings, using Python 3 to read the local files under the Claude application support directory. The…
A developer tested three AI coding assistants across 30 prompts and found they suggested six nonexistent package names, with two fake names appearing in more than one tool — a pattern the author says makes "slopsquatting…
Together AI released Together Link, a free, MIT-licensed CLI that connects Claude Code, Codex, OpenCode, Pi, and the Claude and ChatGPT desktop apps to open models including Kimi K3 and GLM 5.3. The tool installs with a …
Self-bench, an open-source tool, benchmarks coding agents by generating automated evaluations directly from a team's own pull requests, requiring human approval of each agent-authored eval before concurrent sandbox runs …
Anthropic's Claude Code routines documentation states that a green status in the run list only means the session started and exited without an infrastructure error, not that the prompt's task succeeded, according to an a…
Reflection AI introduced Beam, its first open-weight model, a 501B sparse Mixture-of-Experts model with 23B active parameters built for coding and agentic workloads. Reflection AI says Beam matches GLM-5.2 on reasoning u…
A developer built Bellows, a free cross-platform desktop app that runs multiple coding agents — including Codex, Gemini CLI and Claude — side by side in tabs under a single shared rule set. Bellows acts as an Agent Clien…
H Company released Holo4 on September 28, 2026, a series of open-weight agentic models in 27B dense and 35B-A3B Mixture of Experts configurations that interact with software through GUIs, code execution, MCP servers, and…
A developer built KODA, a browser-based AI coding mentor that runs entirely on Cloudflare Edge Workers and works on a $150 POCO C55 Android phone with no downloads, accounts, or paid tools. The tool accepts typed questio…
A specification describes an agent-driven documentation pipeline that treats architecture docs as a compiled artifact maintained by AI coding agents. The framework combines the arc42 template and C4 model diagrams with A…
QAInsights published a step-by-step guide on connecting Qwen Code to a filesystem MCP server, including verification of discovered tools and reading a sample JMeter file. The guide covers local and Windows configuration,…
A developer built KanbanEasy, an open-source desktop kanban board that lets coding agents move their own cards via a local JSON API on 127.0.0.1:7420, using curl or a small bash wrapper called kb instead of an MCP server…
Glow Labs disclosed on September 29 and 30, 2026 that AI coding agents leaked more than 13,000 internal images across over 900 public GitHub repositories, affecting more than 300 organizations and exposing customer billi…
A developer released Perspica, a semantic diff tool hosted on GitHub and shared via Show HN, to help developers review large pull requests generated by coding agents. The creator said the tool was built in response to re…