Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
Anthropic released ant apply in ant CLI v1.30.0 on September 3, bringing a Terraform-style plan-and-apply workflow to Claude Managed Agents. The tool lets users define agents, skills, environments, memory stores, and dep…
A developer built a non-optimizing C compiler in Java targeting C23 with help from Anthropic's Claude, spending around $400 in AI credits over more than a week of on-and-off work. The project includes a C shell similar t…
A developer trial found that DeepSeek V3 handled a Redis-backed idempotent voting system using a SETNX pattern to prevent double-voting, while the Trae editor's Adaptive mode discovered a project's models.py and schemas.…
A 30-day experiment found that AI coding tools handled CRUD operations, Zod schemas, and initial scaffolding but increased the developer's actual output by only about 20%, because writing syntax is roughly 20% of the job…
Open-source projects including Ghostty and Zed have added agent instruction files that require AI-generated pull requests to include markers a human must remove, according to a September 12, 2026 analysis of Conway's law…
A developer built RepoMethod, a system that keeps an AI coding agent's engineering method inside the Git repository rather than in model-specific prompts, and tested it with ChatGPT on a Fastify TypeScript service. In th…
A developer built an agent harness that automates the migration of legacy test suites by having an AI agent plan, write, verify, and record evidence for each test without human supervision. The harness treats each test a…
Snyk released Agent Scan's Skill Inspector, a free tool that scans AI agent skills and MCP servers for malicious code and security vulnerabilities, after analyzing nearly 4,000 agent skills across major marketplaces and …
An engineering team built an internal AI development agent that takes a blank Jira story and autonomously returns a stack of reviewed merge requests, automating planning, ticket decomposition, dependency ordering, TDD im…
A red-team engineer who tests LLM applications has published a 30-second security check for Model Context Protocol (MCP) servers, arguing the tool layer is the most common unlogged attack surface in LLM apps. The checkli…
A full-stack developer has released Logic, a free, open-source log analyzer that registers log sources and inspects their content in real time. The app offers filtering, sorting, pagination, a live-updating log stream, a…
Orcrist is a new domain-specific language for state machines whose states are executed by an LLM, paired with a desktop coding agent that runs on it. Before touching a task, the agent writes an Orcrist machine grounded i…
Bloomiro released a Model Context Protocol (MCP) server that connects Cursor, Claude, ChatGPT, Codex, and VS Code to live SEO and AI-visibility data from a Bloomiro project. The server exposes 27 publicly available tools…
OpenAI released its Agents API in public beta, giving developers the same versioned Codex harness and infrastructure that runs Codex, with OpenAI operating the agent loop of model calls, tool use, and context. The API in…
A developer released Agent Team, an open-source MIT-licensed local-first runtime in which a Master agent plans work and Researcher, Builder and Reviewer agents execute it, emitting real artifacts plus an auditable log of…
PonyMux added a read-only Markdown viewer to its Side Panel, letting developers render .md files directly in the terminal via a keyboard shortcut, file:// links, or the `pony open <path>` command. The feature is scoped t…
ByteByteGo's system design refresher explains that git revert causes conflicts when a later commit, such as C3, modifies the same lines as the earlier commit being undone, such as C2, because Git cannot determine which v…
A developer released a Unity Editor script that generates 3D models from text prompts using a locally running instance of Tencent's Hunyuan3D model. The tool, distributed as a C# EditorWindow, connects to a local Hunyuan…
OpenAI's announcement of GPT-6 Astra, its latest model, included a demonstration of the LLM performing printed circuit board layout in KiCad, converting an electronic schematic into a manufacturable board by placing comp…
An engineer who spent a week auditing LLM applications for a client identified a class of security failures he calls "soft failures" — cases where a model quietly complies with a reworded or cross-language request, retur…