Anthropic's Claude Code uses prompt caching to reduce token costs by reusing stable context prefixes across turns, with cache reads billed at approximately 10% of standard input-token cost, making lon…
A new CLI tool, Decispher, integrates with Grok AI agents to record architectural decisions, providing a persistent memory layer that captures the full trace of agent reasoning—from initial prompt to …
JetBrains tested the Caveman token-compression skill on Claude Code 2.1.200 and found it saves only about 8.5% of output tokens on real agentic tasks, far below the advertised 65%. The skill, which fo…
A developer released Openvisor, a local-first session explorer for OpenCode that lets users inspect tool calls, subagent use, and other session details from exported JSON files stored in the browser's…
Cursor, a fork of VS Code, and Claude Code, a CLI agent from Anthropic, differ fundamentally in architecture and use case, with Cursor offering faster inline edits for feature building and Claude Code…
Developer Mubashir Osmani released agent-mesh, an open-source MCP server that lets AI coding agents such as Claude Code, Codex, opencode, Gemini, and Grok communicate directly with each other, removin…
A packaging error in Anthropic's Claude Code CLI tool version 2.1.88 leaked 513,000 lines of TypeScript source code across 1,906 internal files via npm on March 31, triggering malware campaigns on fak…
A developer built claude-overnight, an open-source tool that queues questions for Claude Code during the day and runs them overnight when usage limits reset, preventing wasted weekly quota. The tool u…
Chron, an MCP server that logs AI coding sessions to a tamper-evident SQLite database, has reached 5,600 installs. The project is evolving from a logging tool to an AI governance layer, adding an Atte…
An AI second brain fails not because of storage limits but because of poor routing, according to an analysis of knowledge management systems. The system can retrieve the wrong context, leading to erro…
A developer shares their minimalist AI coding stack, using VS Code with Cursor, Claude Code as the LLM agent, Tailwind CSS with shadcn/ui for UI, and Vercel for deployment, emphasizing a structured sy…
Google's open-source Genkit framework provides a unified model interface and modular building blocks for building full-stack, AI-powered agentic applications, enabling developers to swap or combine mo…
Directed Memory Bank (DMB) is a tool-agnostic, markdown-based framework that gives AI coding agents persistent project context, eliminating the need to re-explain the stack, auth flow, and constraints…
A developer has created a PreToolUse hook for Claude Code that blocks the AI agent from modifying .env files, preventing accidental overwrites of database passwords and API keys. The 60-line hook inte…
For AI coding agents that need fast, lightweight sandboxing, three Docker alternatives have emerged: Podman, Bubblewrap (bwrap), and Firejail, each with different trade-offs. Podman offers daemonless,…
XT Software Labs has released the NeatContext plugin for Claude Code, an open-source tool that extracts durable knowledge from AI conversations and saves it as reusable context packages. The plugin so…
Cursor currently wins on codebase awareness through its indexing, while Claude Code dominates in autonomous terminal execution and complex refactoring, according to a developer's hands-on comparison. …
Sortie, an open-source tool, automates the process of turning GitHub issues into pull requests by running Claude Code in isolated workspaces with retry logic and state persistence. The tool eliminates…
A new catalog of 1,250 real, compiled SwiftUI components is now available, each shown with a live iOS Simulator screenshot and the exact source code that produced it, designed to be copied directly in…
A developer discovered that Anthropic's Claude Code injects a hidden system-prompt tag, `<ip_reminder>`, on every turn for copyright safety. By grepping their own session logs, they found 151 lines ma…