Full-text search across 56756 articles. Combine with topic and date filters; results sorted by relevance.
A new tutorial demonstrates how to set up a fully local coding agent using open-weight LLMs and open-source harnesses as an alternative to subscription-based services like Claude Code and Codex. The local setup offers tr…
Autonomous medical coding, which uses AI to assign ICD-10 and CPT codes directly from clinical documentation, is emerging as a structural response to coder shortages and rising documentation volumes, according to AHIMA's…
The vibe coding security landscape is diverging into regulation and AI-powered defense, with the EU Cyber Resilience Act vulnerability reporting starting September 2026 and insurers excluding AI-generated code from cover…
Perpeer released Lazychat, a lazygit-style terminal UI that runs Claude Code and Codex coding-agent sessions side by side on macOS 12 or newer, installable via `brew install perpeer/tap/lazychat` or a source `./install.s…
A developer built Taskify, an open-source Claude Code plugin that splits large coding requests into explicit planning, specification, task-breakdown, implementation, review, and fix stages rather than handling everything…
Meta's CLI coding agent Muse Code, launched in August 2026 on Muse Spark 1.2, uses a parent/child architecture in which each write-capable child agent gets its own git worktree rather than sharing a single working copy o…
Trail of Bits spent six months before the Miden zkVM audit building developer tooling with AI agents — an LSP server and VS Code extension, a MASM decompiler, a static analysis engine, and a Lean formal model of the VM e…
Developer Mike McQuaid has open-sourced AgentIDE, a macOS-only "agentic IDE" he vibe-coded with Anthropic's Claude Max and Fable 5 model, replacing Superset, Fork and Zed in his own workflow. AgentIDE is installable via …
Qwen Code, the Qwen team's open-source terminal coding agent, shipped an update and now lists 28k GitHub stars, with its last update recorded in September 2026. The TypeScript project, licensed Apache-2.0, includes auto-…
An eye-tracking study of 53 participants submitted to arXiv on 21 Sep 2026 found that how AI coding interfaces render generated code changes programmers' visual attention, with dynamic rendering producing fewer but longe…
Researchers disclosed a class of configuration injection flaws in September 2026 affecting AI coding agents including Claude Code, Codex, Goose, Qwen Code and Grok Build, tracked as CVE-2026-19592, in which a crafted rep…
A developer built UsageNow, a native macOS menu bar app that aggregates usage data from OpenAI Codex, Claude Code, Gemini CLI, and Antigravity into a single compact view. The app reads local session files and, for Claude…
Aashish Bhandari led a refactor of the alpha Markdown-review application ReviewWithAI using two AI coding agents, with Goku acting as principal architect and implementing developer and Naruto independently reviewing the …
Developer AEndrix03 released Graft, an open-source local-first persistent memory tool for AI coding agents that stores fixes, decisions, and project knowledge in SQLite with sqlite-vec and FTS5 and surfaces them via hybr…
Google released the google-cloud-developer plugin on September 10 from its official google/skills repository, adding Google Cloud authentication, gcloud guardrails, live documentation grounding, and project onboarding to…
A head-to-head test of Cursor, Windsurf, and Claude Code on a 40k-line Next.js project found Cursor's Composer needed 4 tries to fix a React useEffect race condition, Windsurf's Flow took 2 attempts, and Claude Code was …
A 2026 guide by Abhishek Gahlot outlines the three essential functions of a control plane for coding agents—communicating with each agent, translating events into a unified vocabulary, and rendering them—and identifies t…
RocketSim founder and iOS developer Aviel Grossfeld announced the launch of RocketSim 17, a developer tool that integrates the iOS Simulator into AI coding environments such as Cursor, Claude Code, and Codex. The new ver…
A developer built Proofline, a pure Python static analysis tool for the Zero Dependency Hackathon 2026, using only the standard library. The tool parses code with the AST module, builds a caller graph via adjacency lists…
GitHub's Copilot code review always submits a comment review and never blocks a merge, a distinction that is often misunderstood in AI code review procurement. CodeRabbit, Copilot, Cody, and CodeBuddy offer different cap…