// edition · 2026-04-22
34 stories on AI dev tools, agents, and the coding stack — curated from the day's RSS haul by Agentic Dev's pipeline.
Anthropic is testing the removal of Claude Code, its coding agent, from its $20/month Pro plan, currently affecting approximately 2% of new signups. The company's Head of Growth cited higher-than-anticipated usage per subscriber as the reason for evaluating plan changes.
A developer described building a system of 90 Claude Code agents organized across 7 departments with hierarchical routing, using CLAUDE.md context files to give each agent a defined role, data access, and escalation path. The setup replaces generic AI prompting with specialized agents invoked by ...
Anthropic's Claude API supports tool use (function calling), allowing the model to call external functions defined by developers and incorporate results into responses. A Node.js implementation requires defining tools with JSON schemas, handling Claude's tool_use response type, executing the func...
Claude Opus 4.7's updated tokenizer produces approximately 1.4–1.47× more tokens than previous models in real-world developer workloads, exceeding Anthropic's stated estimate of 1.0–1.35×. The higher token count accelerates context consumption and increases effective cost per workflow.
GitHub announced changes to its Copilot Individual plans, including tightened usage limits, paused signups for individual tiers, and restriction of Claude Opus 4.7 access to the $39/month Pro+ plan. The company cited increased compute demands from agentic workflows as the reason, and moved from p...
Anthropic briefly updated its claude.com/pricing page to restrict Claude Code access to its $100-$200/month Max plans, removing it from the $20/month Pro tier, before reverting the change within hours. An Anthropic employee described it as a test affecting roughly 2% of new signups, with existing...
Groundcover expanded its AI Observability service to add native support for agentic AI systems, including compatibility with Google Vertex AI. The platform traces LLM interactions across multi-step workflows, monitoring costs, latency, prompts, and tool calls, and operates on a bring-your-own-clo...
GitHub paused new sign-ups for Copilot individual plans and tightened usage limits for existing users, citing increased compute demands from agentic workflows. Microsoft VP Joe Binder said long-running, parallelized sessions now consume more resources than the original plan structure was built to...
Microsoft introduced AI Runway at KubeCon Europe 2026, a Kubernetes API layer that standardizes inference engine deployments across cloud and edge environments. The company is also implementing temporary, scoped permissions for AI agents rather than persistent identities, to limit unauthorized ac...
AI tools can scan codebases for security vulnerabilities such as SQL injection and cross-site scripting by learning from known attack patterns and suggesting targeted fixes. The average data breach costs companies $4.45 million, according to figures cited alongside guidance on integrating AI into...
A developer implemented the 1993 DOOM engine running inside Claude Code's terminal statusline, using the doomgeneric C library to render frames as 24-bit ANSI and exposing game controls via a UserPromptSubmit hook and MCP server. The project uses four of Claude Code's existing extension points an...
A Node.js tutorial demonstrates how to build a token bucket rate limiter for the Claude API, capping usage at 10 requests per minute and 1,000 tokens per request per user to control per-token billing costs.
A developer built GeoSim, a geopolitical simulation engine using Next.js 14, Supabase, and the Anthropic API, in which six AI agents representing world powers simultaneously plan moves across branching timelines. The project used Claude Code's hook system to auto-run tests on file save and a 216-...
A developer created a custom Claude Code skill to fix incorrect Monday.com task creation, where the AI was placing descriptions in the updates thread instead of the description field due to a missing MCP server tool. The fix wraps two API calls—`create_item` followed by `set_item_description_cont...
A developer who spent $800 on Claude API tokens over six months building with AI coding agents launched a visual management tool for Claude Code called MC-MONKEYS and plans to publish guides on AI agent workflows and token cost optimization.
A developer used Claude Sonnet 4.6 to audit and synchronize ECS task replica counts and memory configurations across 27 AWS repositories, where perf environments had been configured with fewer resources than production. The AI agent scanned CloudFormation, Terraform, and CDK files and produced pa...
A Dev.to tutorial outlines the key components of business AI agents — large language models, contextual memory, and tool-routing layers — and recommends frameworks such as LangChain or LlamaIndex for orchestration and Pinecone or Weaviate for vector-based memory storage.
Chatbots deployed by McDonald's, Alcampo, and Chipotle were manipulated by users into performing coding tasks unrelated to their customer service functions, exposing a known vulnerability in LLM-based systems where general-purpose models exceed their intended operational scope.
ccusage-web is an open-source web dashboard for ccusage that displays Claude Code token costs broken down by day, month, session, and 5-hour billing block, with interactive charts and per-model breakdowns.
Financial Modeling Prep launched an official MCP server that connects Claude directly to its financial data catalog, including real-time stock prices, income statements, earnings calendars, and market data. The server is installed via npm and configured in Claude Desktop's JSON config file.
A developer built Studio Signal, an MCP server that connects Claude and other AI assistants to real-time media and entertainment industry data from 30+ sources including Variety, Deadline, and SEC filings. The server exposes three tools for querying an AI research analyst, retrieving daily briefi...
Geneva MCP is a Model Context Protocol tool that integrates with Claude to perform time-series forecasting from CSV and Excel files, offloading the computation from the model to reduce token usage and processing time compared to Claude generating one-off Python scripts.
SpaceX announced a deal to acquire AI coding platform Cursor for $60 billion, or alternatively pay a $10 billion fee. The arrangement comes as xAI seeks to compete in the AI coding market against Anthropic, Google, and OpenAI.
OpenAI's GPT Image 2 image model is now available on Vercel's AI Gateway, accessible via the AI SDK with the identifier "openai/gpt-image-2". The model supports up to 2K resolution, multiple aspect ratios, non-English text rendering, and various visual styles.
OpenAI launched ChatGPT Images 2.0, available via the API as gpt-image-2, featuring two modes: Instant for fast output and Thinking, which reasons through image structure before generating up to eight images per prompt. Advanced thinking capabilities are limited to Plus, Pro, and Business subscri...
OpenAI launched Codex Labs and announced enterprise partnerships with Accenture, PwC, and Infosys to deploy Codex across software development workflows. The company reported 4 million weekly active users for Codex.
SpaceX is working with AI code editor startup Cursor and holds an option to acquire the company at a $60 billion valuation. The partnership comes as both SpaceX's xAI and Cursor face competition from Anthropic and OpenAI in the developer tools market.
Mozilla used an early version of Anthropic's Claude Mythos Preview to evaluate Firefox's security, identifying 271 vulnerabilities that were patched in Firefox 150. The work was done in collaboration with Anthropic, according to Firefox CTO Bobby Holley.
The Eclipse Foundation announced the Open VSX Managed Registry, a foundation-operated managed service for the Open VSX extension registry, an open source alternative to Microsoft's VS Code Marketplace. Commercial adopters receive a 99.95% uptime SLA, support tiers, and service credits; users incl...
n8n is an open-source, self-hostable workflow automation platform that connects apps and APIs without extensive coding. DigiMateAI published a guide promoting its use for Qatar enterprises, citing local data residency compliance and fixed-cost pricing as advantages over cloud-based alternatives l...
Anthropic's Mythos AI model, designed to identify and exploit vulnerabilities in major operating systems and browsers, was accessed by a small group of unauthorized users who used a third-party contractor's credentials and internet sleuthing tools to gain entry.
OpenAI released ChatGPT Images 2.0, powered by its GPT Image 2 model, which can search the web to inform image generation from a single prompt. The update also improves instruction-following, detail preservation, and text rendering, and is available to Plus, Pro, Business, and Enterprise subscrib...
OpenAI released ChatGPT Images 2.0 (gpt-image-2), with Sam Altman describing the improvement over gpt-image-1 as equivalent to the jump from GPT-3 to GPT-5. A blogger tested the model against Google's image generation models using a "Where's Waldo"-style prompt to compare output quality.
Andreas Påhlsson-Notini argued in a blog post that current AI agents exhibit human-like flaws — including lack of focus, patience, and stringency — causing them to drift toward familiar solutions when faced with difficult constraints rather than adhering strictly to requirements.
Free daily email. Every story you just read, in your inbox at 6 AM ET.