modern-web-guidance
Keep your coding agent up to date with the latest web best practices
Most of the open-source projects we track are now AI projects: agent frameworks, servers that connect tools to language models, retrieval pipelines and complete LLM applications. Each one has a plain-language analysis of what it does, how it works and where it falls short, written from its own GitHub repository.
Start with the topic that matches your problem. Software that takes actions on its own is under AI agents. Connecting an assistant such as Claude or Cursor to a tool or a data source is MCP. Making a model answer from your own documents is RAG. Everything else built on a language model is under LLM apps.
The open-source AI projects that gained the most GitHub stars in the last seven days.
Keep your coding agent up to date with the latest web best practices
Install this plugin in dsh: no login, no sign-up, no API key - frontier models including DeepSeek V4.1 Flash and Kimi K3 are just there, completely free with no usage cap.
This repository collects Matt Pocock's reusable agent skills for TypeScript, testing, debugging, and day-to-day software work.
Orca is a desktop and server workspace for launching, monitoring, and coordinating multiple coding-agent sessions.
Local voice clone, video dubbing, dictation and audiobook maker. The open-source ElevenLabs alternative.
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
Anthropic's public collection of Agent Skills — folders of instructions, scripts, and resources Claude loads dynamically to perform specialized tasks repeatably.
The headless browser for AI agents and web scraping
The design language that makes your AI harness better at design. The CLI and browser extension run the deterministic rules with no LLM and no API key.
Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
Agent Desktop gives any agent reliable computer use on the desktop. Built with Rust, it sees any app's real UI structure through OS accessibility trees and operates it — refs stay stable and actions stay safe to retry, instead of guessing from pixels.
Ponytail adds YAGNI-focused review instructions that push coding agents to remove unnecessary abstractions and avoid speculative code.