Tag: claude-code

AgentHub is a privacy-first macOS app that unifies Claude Code and Codex session management. Monitor agents in real time, review diffs inline, manage Git worktrees, and preview on iOS Simulator—all running locally with no data collection.

alinaqi/claude-bootstrap is an open-source MIT-licensed toolkit that transforms Claude Code into a test-enforced, multi-agent engineering system with 67 skills, persistent memory, and 13-tier model routing.

happier-dev/happier is an open-source, MIT-licensed client for Claude Code, Codex, OpenCode and other AI coding agents. It provides end-to-end encrypted, cross-device session control via mobile, web, and desktop apps with full self-hosting support.

lackeyjb/playwright-skill is a Claude Code Skill that enables autonomous Playwright browser automation through natural language prompts. MIT-licensed with 2,920 GitHub stars, it generates custom automation code on demand with visible browser execution.

kepano/obsidian-skills provides standardized agent skills for Obsidian, enabling AI agents to work with Markdown, Bases, JSON Canvas, and the Obsidian CLI across Claude Code, Codex, and OpenCode.

ryanstephen/lil-agents is an open-source macOS app that places animated AI companions on your dock, providing instant popover terminal access to Claude Code, OpenAI Codex, GitHub Copilot, and Google Gemini CLI.

Install druckenmiller.skill for Claude Code to run Stanley Druckenmiller's billionaire investment framework daily. Four weighted signals, authentic persona responses, and zero cost.

Discover Buffett-Perspective, a Claude Code Skill that embeds Warren Buffett's 60-year cognitive framework into your AI workflow. Features 6 mental models, 8 decision heuristics, and explicit internal tensions for superior technical decision-making.

Caveman is a Claude Code skill that cuts 75% of AI output tokens by making agents talk in terse 'caveman speak' while preserving 100% technical accuracy. Install in 30 seconds, save on inference costs, and iterate faster.

We tested the leading AI coding agents of 2026. Here are the tools that genuinely write, debug, and ship production-ready code.

DeepScientist is a local-first autonomous research studio that transforms fragmented research work into a persistent AI workspace. With 15-minute setup, Findings Memory, Bayesian optimization, and four built-in runners, it keeps experiments running and papers shipping.

Stop terminal-watching! Claude Task Viewer transforms Claude Code's hidden task data into a real-time Kanban board with dependency visualization, desktop notifications, and Gantt timelines. Install instantly with npx.

Tokscale is a high-performance Rust-powered CLI tool that tracks token usage and costs across 20+ AI coding assistants including Claude Code, Cursor, Codex, and OpenCode. Features interactive TUI, real-time pricing, social leaderboards, and 10x faster native processing.

Claude Code Router lets you route AI coding requests to cheaper, faster models while keeping Anthropic's exceptional CLI interface. Cut costs by 90% with intelligent task-based routing to DeepSeek, Gemini, Ollama, and more.

Discover how AutoResearch automates code optimization with traceable results. From 53% Shopify speedups to 10x GPU kernel gains, explore real implementations and start your own self-improving loop.

Open Ralph Wiggum is a TypeScript CLI that wraps Claude Code, Codex, Copilot CLI, Cursor Agent, Qwen Code, and OpenCode in a self-correcting autonomous loop. Built on Bun with MIT licensing, it enables iterative AI coding without manual retry babysitting.

Discover 50+ production-ready Claude Code plugins that transform your AI assistant into an autonomous development powerhouse. From 500+ app integrations to security scanning and multi-agent orchestration, learn how to supercharge your workflow.

tweakcc is a CLI tool that patches Claude Code to enable deep customization of system prompts, themes, toolsets, and UI elements. Supports native and npm installations across all platforms with automatic reapplication after updates.