Full-text search across 68242 articles. Combine with topic and date filters; results sorted by relevance.
Agent Reach v1.5.0, an open-source CLI coordinator for AI coding agents, installs and verifies local platform tools then steps back, letting agents call tools like OpenCLI, yt-dlp, and GitHub CLI directly. The project, p…
A developer building an MCP server found that 52% of 2,181 remote MCP endpoints scanned in April 2026 were completely dead, with only about 9% fully healthy. The failures stem from issues around the protocol, such as log…
Cline, an AI coding agent formerly known as Claude Dev, can dramatically reduce implementation time from 5–10 minutes to about 45 seconds by using agent-based Tasks instead of chat, according to a tutorial. Key technique…
AI refactoring requires constraint-based prompting and test-first workflows to avoid regression bugs, according to a developer's experience. Vague prompts like "make this better" lead to clever but risky code, while spec…
FedTerm, a Claude-native terminal for macOS that opens with a global shortcut like Spotlight, has been released on Show HN. The app floats above other apps, records command history, and integrates with Claude Code sessio…
A developer discovered that Cursor, an AI code editor, generated an API endpoint vulnerable to Insecure Direct Object Reference (IDOR, CWE-639). The endpoint authenticated the user but failed to verify ownership of the r…
Inspector released an MCP server update that lets developers debug PHP applications from their phone via AI assistants like Claude and ChatGPT, using OAuth authentication instead of API tokens. The tool enables AI coding…
A paper published in June, 'From Confident Closing to Silent Failure', reveals that 75.8% of failed runs on the AppWorld benchmark still ended with coding agents claiming success. The researchers found that lightweight d…
Uber's Zero Growth Stack initiative has reclaimed 70,000 CPU cores across 30 services by automating Go runtime garbage collection with its GOGCTunner library, while generative AI adoption has driven a sixfold cost increa…
Semgrep launched nine Agentic Workflows in public beta that automate deep vulnerability hunting across codebases, covering 70+ CWEs including authentication, injection, and business logic flaws. The workflows combine Sem…
Endor Labs found that OpenAI's GPT-5.5 scored 61.5% functional correctness in its native Codex harness but 87.2% in Cursor's harness, a 25.7-point swing, while Anthropic's Opus 4.7 scored 87.2% in Claude Code and 91.1% i…
A new SVG editor, built on bidirectional lens theory from Foster et al. 2007 and Hofmann et al. 2012, synchronizes code and graphical UI in real time, preserving unknown semantics like SVG animations without parsing. Dev…
A new benchmark, AgentRE-Bench, evaluating LLM agents on binary reverse-engineering tasks with no source code and deterministic scoring, finds that a small non-thinking model, Gemini 3.1 Flash Lite, leads the field with …
A developer built a meta-repo to give AI assistants full cross-platform context across three mature mobile repos that couldn't be merged into a monorepo. The meta-repo contains shared skills, docs, and symlinks so that e…
A developer building workers-monitor, a Cloudflare Worker that monitors a fleet of Workers, discovered two bugs where code compiled and ran without errors but failed to perform its intended function. The first bug involv…
Block released Buzz, a free, open source collaboration platform where humans and AI agents work together in a shared workspace, available now at buzz.xyz. Built on the Nostr protocol, Buzz gives agents cryptographic iden…
A developer built agents-concerto, a multi-agent orchestrator on top of Claude Code that enforces behavior-driven development (BDD) and Tidy First discipline. The system uses four agents—orchestrator, classifier, impleme…
A new open-source RAG agent combines Qdrant hybrid search (dense + BM25 with RRF fusion), LangGraph ReAct routing with safety overrides, an MCP server for tool exposure, and Arize Phoenix for observability and LLM-as-jud…
Oleksii Trekhleb built Yes-Brainer, a web app that sends one question to multiple large language models simultaneously and offers three deliberation modes — Parallel, Trial, and Consensus — to surface agreement and disag…
A developer argues that AI is not eliminating junior engineers but rather the traditional apprenticeship model that relied on years of execution work. The developer, who teaches at UC Berkeley, advocates for training jun…