Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
Evil Martians, a design and engineering consultancy, migrated its corporate website and blog from Gatsby to Astro in nine days with a single engineer, cutting homepage JavaScript at load by 61% and raising mobile Lightho…
A developer argues that current agentic coding tools like Claude Code and Codex are not yet capable of reliably running 10 or more agents simultaneously, citing bottlenecks in isolation, compute, and merge management. Th…
Omarchy, a Linux distribution, now routes crash dumps from systemd-coredump to a user's default coding agent via a desktop notification, attaching a 'diagnose-crash' skill to guide analysis. Users can trigger the same an…
Omarchy 4, a Linux distribution, allows users to set Claude Code as the default coding agent with the command `omarchy default agent claude`, or via Setup › Defaults › Agent in the Omarchy Menu. The system pre-wires ten …
Evil Martians migrated its website from Gatsby to Astro in under two weeks in August 2026, using Claude Code, after postponing the move for three years due to high costs and complexity. The migration involved 470 files a…
Aispace.sh released an open-source, scriptable CLI for secure temporary file sharing designed for AI agents and humans, featuring expiring links, predictable JSON output, and optional local age X25519 encryption. The cli…
Brw, an open-source semantic browser control tool by Revitt, claims to outperform Claude-in-Chrome in pre-release head-to-head tests by using fewer turns and fewer tokens, acting from stable refs like 'e17' instead of sc…
The Driscoll Public AI, version 2.4.1, was published to the official MCP registry on 2026-09-07 as a hosted remote over streamable-http, according to the mcpindex.ai index. The index's semantic screen found no manipulati…
Mcp-context-card v1.0.1, an MCP server for project context, memory, and identity, was published to the official MCP registry on 2026-09-07 and is distributed on npm under the Memory & RAG category. The mcpindex integrity…
OpenHCS v0.8.2, a tool for inspecting, authoring, validating, and running high-content microscopy workflows, was published to the official MCP registry on 2026-09-07 and is distributed as openhcs on PyPI. The MCP index's…
A developer explains how Markov Decision Processes (MDPs) form the foundation of reinforcement learning, shifting from hardcoded if-else rules to a mathematical framework that lets AI agents learn through trial and error…
ParseAPI (com.parseapi/mcp@0.3.2), an official MCP server for place, IP, email, phone, weather, and currency lookups, was published to the official MCP registry on 2026-09-07. The server, distributed as parseapi-mcp on n…
Io.github.aligndottech/cli, a cross-tool decision memory server for AI coding agents, was published to the official MCP registry as version 0.37.1 on 2026-09-07, according to the mcpindex.ai registry. The server passed a…
Archprint, a new open-source tool announced on Hacker News, automatically infers architecture lint rules from a repository's import graph, generating enforcement rules for TypeScript projects without manual authoring. Th…
Hermes Kanban, a durable task board for multi-agent profile collaboration, is now available, allowing multiple named agents to work on tasks via a shared SQLite database and a dedicated kanban_* toolset. The board suppor…
Developer Ben Oror has launched Inbundly, an open-source browser extension that reintroduces Google Inbox-style email bundling to Gmail. The tool groups emails by label into collapsible bundles, supports custom rules and…
A developer's blog post explains that an AI agent is not a smarter language model but a model surrounded by five parts—tools, memory, and a framework—that enable it to act. The framework, such as LangChain, wires these p…
A developer argues that as AI agents grow more capable, nearly everything — from corporate systems to consumer devices — will need to become "agent-addressable" through code, creating a feedback loop akin to the one betw…
A developer shared a technique for ensuring large language models return valid JSON, describing a three-layer approach with a repair loop. The method aims to improve reliability when integrating LLMs into full-stack appl…
A developer has turned a Steam Deck into a server node for the BarkVisor homelab platform, enabling it to run VMs and local AI models via Ollama while remaining a gaming device. The walkthrough details installing BarkVis…