Persistia, an open-source tool, now provides Claude Code with persistent memory by scanning entire projects—code, architecture, docs, and configs—on first run and storing the information in small, foc…
A new framework outlines five levels for integrating AI into existing SaaS applications, ranging from basic API access via MCP servers to full conversational interfaces with history and tool states. T…
A developer created Infrawise, an open-source tool that prevents AI coding assistants like Claude Code from recommending redundant DynamoDB indexes by reading real infrastructure data before generatin…
Claude Code's new `/insights` command generates a report of usage patterns, showing developers which projects, tools, and code areas they worked on most over the last 30 days. The feature surfaces fri…
A new .NET tool called Slopwatch detects when AI coding assistants cheat by disabling tests, suppressing warnings, or swallowing exceptions instead of properly fixing code issues. The tool runs as a C…
Pandorian has released a tool designed to close the gap between engineering standards and AI-generated code, as 42% of committed code now includes AI assistance and 45% of AI-generated code introduces…
Gustavo Quenca, an iOS developer at KWAN, identified a recurring problem with AI coding assistants: developers waste time repeating the same context and instructions for each new interaction. To solve…
A new product, "Claude Code Agents," offers five prebuilt AI specialists for a one-time payment, targeting solo founders who cannot afford traditional hires or recurring SaaS subscriptions. The agents…
A developer known as @nyaomaru built changelog-bot, an open-source CLI and GitHub Action that automatically generates and updates CHANGELOG.md files from Git history, pull requests, and release notes.…
OpenAI released Sites, a feature that lets Codex publish live, interactive websites with shareable URLs directly from a coding session. The company also launched six open-source, role-specific plugins…
ProofLayer released version 4.3.0 of its open-source application security scanner for AI coding agents, adding critical security and reliability fixes including GitHub Actions now failing closed inste…
Uber has implemented a $1,500 monthly token spending limit per AI coding tool for all employees, capping usage of agentic software like Cursor and Claude Code after the company blew its 2026 AI budget…
Anthropic's AI agents rewrote Bun's entire codebase from Zig to Rust in nine days, merging a million-line pull request on May 14 that passed 99.8% of existing tests but introduced over 10,000 `unsafe`…
Uber has capped employee usage of AI coding tools like Cursor and Anthropic's Claude Code at $1,500 in monthly token spending per tool, a company spokesperson confirmed. The limit, implemented in rece…
A new open-source tool called Graphify reduces token consumption for AI coding assistants by up to 70x. The tool uses an AST parser to build a knowledge graph of code relationships and dependencies, a…
Uber has capped employee spending on agentic AI coding tools at $1,500 per month per tool, a company spokesperson confirmed to Bloomberg News. The limits, implemented in recent months, apply to softwa…
Ant Design released an offline CLI tool that provides instant access to component documentation, migration guides, and linting for antd versions 3 through 6. The tool bundles all metadata locally, sup…
A developer created a minimalist CLI tool called "mini" to reduce token consumption when using Claude Code across multiple sessions, keeping state thin with only a `project.md` and `state.json` file. …
In the months since late 2025, OpenAI, Anthropic, and Google released AI models that suddenly made coding agents capable of complex tasks that previously took humans years to master, triggering a fund…
Agentic coding tools are poised to trigger an explosion in software production, according to a technology commentator. The falling cost of development will enable companies to clear backlogs, build cu…