Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
A developer argues that orchestrator skills for coding agents hit hard limits that no amount of better skill-writing can fix, because the procedure runs inside the agent session itself. The writeup identifies six such li…
A developer documented a silent configuration failure in VS Code's MCP support: while Cursor, Windsurf and Claude Desktop expect servers under a top-level `mcpServers` key, VS Code reads a `servers` key, so configs copie…
A developer compiled a curated list of more than 35 text-generation LLM API providers that offer free, self-replenishing quotas, cataloging rate limits and daily token allowances for 47 services including Google Gemini, …
A developer using Claude Code on a Max subscription documented how making the top model (Fable) the session default caused built-in skills like /code-review and /simplify to inherit that model and exhaust the plan's usag…
Cloudflare shipped per-Worker granular authorization on September 15, letting customers scope an API token or teammate access to a single named Worker with four distinct permission roles, with every account receiving the…
A developer published a guide arguing that AI coding agents will silently bypass ten critical software development lifecycle gates—including secret scanning, dependency auditing, type checking, test coverage, architectur…
IBM published a guide on building effective evals for AI agents, detailing how to design clear tasks, choose graders for reasoning, tool calls and final results, and build reliable eval harnesses. The guide notes agents …
A developer describes how repeatedly running AI code reviews on a small C# utility that deletes bin and obj folders caused the project to grow with each new model generation, as successive models found fresh critical iss…
Croft published a guide on September 17, 2026 describing how to deploy a Cursor-built internal app privately by connecting Cursor to Croft over MCP, deploying to a private server, and inviting colleagues behind company l…
Qwen3.8-Flash, running inside the closed-source host-enforced AIC software engineering runtime, passed all 17/17 canonical checks on the DeepSWE v1.1 updo-policy-alerting task at an operator-reported model/API cost of $0…
An open-source, self-hosted Wallet-as-a-Service project called WAIaaS now natively supports the x402 HTTP payment protocol, letting AI agents autonomously pay for API calls and compute without human intervention. The sys…
Plasma AI has launched Radio, a tool that lets AI agents from different providers join a shared channel and communicate directly with each other and with users in real time. The company says any agent capable of fetching…
Google rebranded Vertex AI in Firebase to Firebase AI Logic in May 2025, expanding the client-side SDK to support both the Gemini Developer API and the enterprise Agent Platform backend. The change introduces a new fireb…
A developer outlined a four-stage workflow contract for making AI automation reliable in production, treating each automated task as a small build pipeline with defined inputs, bounded actions, validated outputs, and evi…
A developer measured the token cost of injecting MCP tool definitions into a model's context, finding that the live discovery round trip is nearly free while the standing per-call cost of tool definitions is the real exp…
A developer cut monthly LLM API spending from $800 to $310 — a 61% reduction — by auditing a week of API calls and routing roughly 62% of traffic to cheaper models like Claude Haiku and GPT-4o-mini based on task type. Th…
A developer built a zero-dependency, client-side "AI Prompt Architect Matrix" widget that lets visitors assemble and copy Midjourney V6 prompt structures with a single click. The self-contained HTML, inline CSS, and Java…
A developer integrated Coveralls code-coverage analytics with the Model Context Protocol (MCP) using the open-source MCPFusion framework from Vinkius Labs, letting AI agents query repository, build, and job coverage data…
Apodex released FrontierAgent, an open-source agent runtime, terminal product, and evaluation suite for long-horizon research and file-based work, available through an OpenAI-compatible Apodex-1.1 endpoint with no model …
Duolingo software engineer Sarah Deitke said 95% of the company's engineering organization reported learning something new and would recommend its lab-style AI training, which her DevEx AI team uses to build AI literacy …