Full-text search across 57211 articles. Combine with topic and date filters; results sorted by relevance.
GitHub has shipped a pre-commit vulnerability scanning feature for Copilot, available to all subscribers including Free tier users. The slash command scans uncommitted diffs for five OWASP vulnerability classes—injection…
REA, a new open-source tool released on GitHub, enables AI agents to reverse engineer binary code from apps without source code, using 68 tools and Hopper for deep native analysis. The tool, installable via npm or curl, …
A developer built agentproto, a daemon and CLI that unifies the lifecycle of multiple AI coding agents—Claude Code, Codex, Hermes, opencode, and Mastra—under a single interface with durable supervision, policy gates, and…
The International Council of Museums (Icom) adopted a revised code of ethics on June 25, addressing AI, climate change, and colonialism. The new code, approved by 85.9% of members, replaces the 2004 version and aligns wi…
N3MO, a deterministic code intelligence tool that parses source code ASTs into a queryable knowledge graph without embeddings or LLM calls, launched on Hacker News. It enables transitive dependency mapping, blast radius …
Anthropic's Claude Code and Claude Agent SDK enable developers to build agentic applications by combining a terminal-based agent loop with a programmable SDK. The SDK's query() function returns an async stream of typed m…
A developer forking the open-core Meetily product with AI coding tools reports that implementing speaker diarization requires a full pipeline redesign, as the legacy code for the feature is not wired into the active tran…
A developer explains why they refuse to run untrusted AI models in coding agents, citing risks of backdoored code and arbitrary execution. They trust only Anthropic and OpenAI due to legal and financial incentives, while…
Developers are adopting local proxy routers like Weave and 9Router to cut API costs and bypass the context re-read tax in AI coding assistants such as Claude Code and Cursor. These routers intercept API calls, route task…
On-premises AI coding tools enable enterprises to safeguard sensitive code, ensure data residency, and maintain compliance without compromising performance. By deploying AI within their own infrastructure, organizations …
Developer Lenn Voss introduces Recall, an open-source tool that uses classical NLP algorithms like TF-IDF and TextRank to summarize Claude Code sessions locally, bypassing expensive LLM calls and cloud dependencies. The …
Engineers are shifting from better prompting to better control systems for autonomous coding agents, designing systems with goals, evaluators, loops, and artifacts that allow agents to work without constant human steerin…
Dropbox has unveiled Nova, an internal platform designed to orchestrate AI coding agents across its engineering workflows, enabling automated tasks such as flaky test remediation, dependency migrations, and production in…
GitHub has released two public previews for Copilot code review: agent skills with MCP support that incorporate organizational context into reviews, and a new medium analysis tier that routes complex pull requests to a h…
Arm's Product Security Team has released Metis, an open-source AI security framework that uses large language models to perform deep reasoning and context-aware code reviews for detecting subtle vulnerabilities. The tool…
On May 18, Cursor released Composer 2.5, a coding model that matches frontier performance at roughly one-tenth the cost, scoring 79.8% on SWE-Bench Multilingual and 63.2% on CursorBench v3.1. The model runs on Moonshot A…
At Google I/O 2026, Google released Antigravity 2.0, an "agent-first" development platform that removes the traditional IDE and replaces manual coding with natural language intent and autonomous AI agents. The platform e…
This article provides a guide for building a self-hosted AI code review tool in Python using Ollama and a locally-run language model like CodeLlama or DeepSeek-Coder. The tool reads a git diff, sends it to the local mode…
The author uses 18 static structure tests, running in 0.4 seconds, to prevent AI coding assistants like Claude Code from violating critical architectural boundaries in a complex FastAPI/IoT system. The key example shows …
A developer built UECA-React, a React framework designed for AI coding agents in which every component follows an identical shape — a struct (props, events, methods, children, lifecycle), a model hook, and a functional c…