Full-text search across 57821 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's Claude Code agent suffered a statistically significant five-day performance degradation immediately before the Opus 4.8 model release, with pass rates dropping from a 65% baseline to as low as 50%. The drop c…
A developer has proposed a framework for deciding which software engineering tasks to delegate to Claude Code and which to handle personally, dividing work into routine, engineering, and creativity categories. The develo…
A developer built Aigent.ly, an open-source vulnerability prevention layer that sits between users and AI coding tools like Cursor and GitHub Copilot. The tool monitors the AI's security context in real time to flag stal…
The open-source AI coding agent pi, from the earendil-works project on GitHub, has surpassed 46,000 stars and offers a terminal-based assistant that reads files, writes code, runs shell commands, and iterates on tasks wi…
SpecFlow, a new CLI tool from developer ceatoleii, installs Spec-Driven Development (SDD) in any repository by enforcing a four-phase agent pipeline where only a single "Implementer" agent can edit source code. The tool …
A firefighter, an entrepreneur, and a dad used AI tools to build custom apps solving everyday problems without writing code. The non-technical users instructed chatbots like Claude and Lovable to create solutions for gro…
Project IDX is a browser-based development environment that integrates AI-driven security linting to help beginners write safer code from the start. The tool actively flags potential vulnerabilities, such as unprotected …
Stephan and Thomas open-sourced Semble, a code search tool for AI agents that uses 98% fewer tokens than grep+read by combining static Model2Vec embeddings with BM25 and code-aware reranking. The tool indexes a typical r…
AI-generated "vibe-coded" tools are flooding the internet, but most are useless to anyone except their creators, argues a developer. These tools lack reach, social integration, and finish—three qualities that make tools …
Developer cjodo released claude-colorizer, a dependency-free Go tool that renders color literals from Claude Code conversations as live statusline swatches and changes terminal tab and background colors across working, n…
Graphify, an open-source Apache 2.0 tool, builds a code knowledge graph from a codebase by parsing it locally with tree-sitter across 36 languages, representing functions, classes, config and docs as nodes and calls, imp…
Developer aldi949 released Truth Firewall, an open-source verification tool that blocks a coding agent's "DONE" claim until mandatory acceptance checks pass on the final repository state. Truth Firewall runs on Windows P…
A bootstrapped developer launched JackHamr, a cloud platform that provisions teams of specialized AI coding agents, each running on its own cloud instance with VS Code, terminal, browser, Docker and Git preinstalled at u…
Phonebook, a tool released as agent-phonebook@0.4.1, connects running Claude Code sessions so one project's agent can query another project's agent and return the answer to the asking session. The tool requires Claude Co…
A developer released Agent Scrub, a macOS 14+ menu-bar tool that scans and redacts plaintext API keys, tokens, and other secrets stored in the local conversation history of AI coding agents including Claude Code, Codex, …
A developer outlined four habits for using AI coding assistants like Copilot, Claude, and Cursor as thinking partners rather than code generators, including a 15-minute rule for debugging and a structured context format.…
A developer built a three-stage deploy gate that lets a fully autonomous Claude Code-based coding agent merge and ship its own pull requests safely, after an early incident where a currency-blind cache took down a checko…
The Cloud Security Alliance's AI Safety Initiative published a research note on April 19, 2026, finding that 440,445 of 2.23 million code samples generated across 16 code-generating models in Python and JavaScript — 19.7…
Research software engineer Matt Archer published a decision framework advising against using LLMs to refactor legacy scientific code unless the refactor serves a concrete user need, because an LLM lowers the cost of writ…
A developer built an on-call MCP toolkit that lets Meta's Muse Code terminal coding agent perform the first ten minutes of an incident investigation while enforcing per-identity tool access at Kong AI Gateway 2.0. The ga…