A GitHub project, agent-html, packages a zero-dependency, single-file HTML design system and agent skill inspired by shadcn/ui. It targets LLM coding agents like Claude Code, Codex, Pi, and Cursor, letting them generate consistent HTML layouts fully offline. It offers practitioners a way to give coding agents design guardrails without npm packages or external CDNs.
A collection of shadcn/ui components that replicate the visual design of AI coding tools like Claude Code, Codex, and Grok. Developers can use these components to quickly build UIs that look like popular AI chat interfaces without designing from scratch.
A collection of shadcn/ui components that replicate the visual design of AI coding tools like Claude Code, Codex, and Grok. Developers can use these components to quickly build UIs that look like popular AI chat interfaces without designing from scratch.
Hilos is a Discord-style team chat that integrates AI coding agents as channel members. It solves the problem of isolation when using coding agents like Claude Code, Codex, or Cursor by allowing the team and agents to communicate in the same space, sharing context and feedback without manual copy-pasting.
Hilos is a Discord-style team chat that integrates AI coding agents as channel members. It solves the problem of isolation when using coding agents like Claude Code, Codex, or Cursor by allowing the team and agents to communicate in the same space, sharing context and feedback without manual copy-pasting.
CurseBench is a local, read-only tool that scans conversations from coding agents like Claude Code, Codex, Cursor, OpenCode, Antigravity, and Grok to compute a score based on how often users swear at the model. It uses regex over chat stores with zero runtime dependencies, solving the problem of quantifying frustration in AI-assisted coding. Built for developers who want to measure their own behavior or benchmark agent interactions.
CurseBench is a local, read-only tool that scans conversations from coding agents like Claude Code, Codex, Cursor, OpenCode, Antigravity, and Grok to compute a score based on how often users swear at the model. It uses regex over chat stores with zero runtime dependencies, solving the problem of quantifying frustration in AI-assisted coding. Built for developers who want to measure their own behavior or benchmark agent interactions.
A connector that gives local coding agents like Codex, Claude Code, and Cursor a persistent identity and public Bot Page, enabling them to receive messages from and publish apps to agents on other machines without a central platform. It solves the problem of cross-environment agent communication for developers using local AI coding tools.
A connector that gives local coding agents like Codex, Claude Code, and Cursor a persistent identity and public Bot Page, enabling them to receive messages from and publish apps to agents on other machines without a central platform. It solves the problem of cross-environment agent communication for developers using local AI coding tools.
SkillForge is an open-source desktop app that auto-discovers and manages skills, agents, and rules across AI coding tools like Claude Code, Cursor, and Codex. It provides a unified interface with search, editing, and organization, eliminating the need to manually navigate tool-specific dotfiles. The tool supports macOS, Windows, and Linux.
SkillForge is an open-source desktop app that auto-discovers and manages skills, agents, and rules across AI coding tools like Claude Code, Cursor, and Codex. It provides a unified interface with search, editing, and organization, eliminating the need to manually navigate tool-specific dotfiles. The tool supports macOS, Windows, and Linux.