Ambykit
AmbyKit, a spec-driven development tool for AI coding assistants, launched to let developers author requirements once and emit native commands for multiple assistants including Claude Code, GitHub Copilot, and Cursor. Th…
Full-text search across 64038 articles. Combine with topic and date filters; results sorted by relevance.
AmbyKit, a spec-driven development tool for AI coding assistants, launched to let developers author requirements once and emit native commands for multiple assistants including Claude Code, GitHub Copilot, and Cursor. Th…
Neo4j has released Laravel Boost, an open-source package that integrates the official Neo4j MCP server into Laravel Boost, giving AI coding assistants live access to a Neo4j graph database and application architecture. T…
OpenAI acquired German startup Ona, formerly Gitpod, on June 11, 2026, to provide persistent cloud execution for its Codex coding agent, which now has over 5 million weekly active users. The deal shifts the AI coding bat…
AI engineering productivity gains of 3x or more are now documented across multiple companies, with NVIDIA reporting a 3x increase in committed code across 30,000 developers with flat bug rates, Amplitude tripling weekly …
Refuse, a pre-install security shim that blocks vulnerable package installs before they reach the disk, has launched to address a surge in supply-chain attacks targeting AI coding agents. The tool intercepts install comm…
Omp, a terminal-based coding agent forked from Pi, differentiates its subagent system by allowing workers to return typed results matching a declared schema, send direct peer messages, and safely edit shared files, rejec…
Anthropic made Claude Sonnet 5 the default model for all Free and Pro users on June 30 at $2 per million input tokens and $10 per million output, half the price of Opus 4.8, while performing at Opus levels on roughly 80%…
LM Studio launched LM Studio Bionic, a new Mac app that uses open models for coding, research, and document work, with support for local and cloud-based open-source models under a Zero Data Retention policy. The app incl…
A developer launched S8sskills.com, an open-source repository of serverless skill bundles that teach AI coding agents how to deploy on major cloud providers. The project offers one-command installation of version-control…
Datopian released PortalJS, an open-source, AI-native framework for building data portals that uses agentic skills to help teams choose an architecture, scaffold it, and load data. The framework ships with Claude Code sk…
A study introducing PoPE (Popperian Placebo-controlled Evaluation) found that small frozen code models with 0.5 to 1.5 billion parameters do not meaningfully learn from their own errors when generating code. In prompt ch…
A developer who shipped a client reporting tool built with Bolt.new found that while the AI-generated code was correct, it failed under concurrent load due to missing indexes, an under-configured connection pool, N+1 que…
Paper has launched Paper Desktop, a connected design canvas that integrates with apps, agents, and code repositories via the Model Context Protocol (MCP), enabling a continuous design-to-code workflow. The HTML/CSS-based…
Coding agents lower the cost of writing code, but the default is to spend those savings on more features. The author argues that teams should instead spend the AI dividend on quality, using agents to simplify designs, ex…
A developer realized they could review code but not write it from scratch after relying heavily on AI for coding since mid-2024. The engineer froze when trying to write an HTTP handler in Go from memory, highlighting the…
DaoXE, a multi-protocol API gateway operated by its developers, exposes more than Chat Completions and supports live model discovery. The team provides a practical setup path for coding assistants like Cline, Continue, R…
A developer built Maestro AI, a harness-agnostic model router that routes LLM calls to appropriate models based on task complexity, preventing expensive models like Claude Sonnet from being used for simple tasks. The sys…
OpenAI released GPT-5.6 Sol, which scores 59 on the Artificial Analysis Intelligence Index, one point below Claude Fable 5, at approximately one third the cost. The model family includes Sol, Terra, and Luna, with Sol le…
A security researcher disclosed a pull-based prompt-injection attack called HalluSquatting that targets coding assistants and agentic tools including Cursor, Gemini CLI, Windsurf, and GitHub Copilot. The attack exploits …
An open-source plugin called claude-mem, created by indie developer Alex Newman, gives Anthropic's Claude Code persistent memory by storing session summaries locally in a SQLite database. The plugin gained 46,000 GitHub …