JavaScript
Stop Writing Prompts Manually. How to Turn AI Agents into an Autonomous Assembly Line
Boris Cherni from Anthropic no longer writes prompts manually—automatic loops do it instead. Here's how Loop Engineering changes the game.
#claude-code
46 projects Go
How to Tame the Chaos of a Dozen AI Agents in One Project
Kandev is an open Kanban-based platform that orchestrates multiple AI coding agents, using Git worktree for conflict-free parallel execution.
TypeScript
How to Teach Claude Code to Watch Videos and Understand What's Happening on Screen
A plugin for Claude Code that converts video into frames and timestamped transcripts, letting the AI analyze screen recordings and YouTube videos directly in the terminal.
Python
Full SEO Audit Right in the Terminal with the Claude SEO Plugin
A CLI extension for Claude Code that automates SEO audits, generates actionable roadmaps, and validates technical issues directly in the terminal.
Unknown
How to Turn Claude Code into an Operational Partner with makerskills
Turn Claude Code into an operational partner with makerskills—a plugin offering 19 structured scenarios for AI agent environments that handle research, knowledge management, and financial planning.
Python
Uber Open-Sources AI Agent Protection System ADR
Uber open-sourced ADR, a system for detecting and responding to threats targeting AI agents. The project includes telemetry collection, a benchmark with 303 tasks, and a two-level threat detection module.
Python
Knowledge Graphs Instead of Gigabytes of Embeddings for Code Analysis in Monorepos
Developer Vitaliy built code-graph-rag to replace vector search with knowledge graphs for monorepo code analysis. It uses Tree-sitter, Memgraph, and Qdrant to understand code structure.
JavaScript
How to Save AI Assistants from Context Degradation with the GSD Core Framework
How to prevent AI assistants from degrading mid-session. GSD Core framework uses sub-agents and a 5-step workflow to keep context clean and code quality high.
TypeScript
Controlling AI Agents from a Messenger with botmux
botmux turns Feishu/Lark messenger into a remote control for console AI agents like Claude Code and Codex, letting you manage heavy CLI tasks from your phone.
TypeScript
Turning Claude Code into an Automated Development Powerhouse
Developer Dave Poon built buildwithclaude, a marketplace and knowledge base for Claude Code users that aggregates thousands of plugins, subagents, and MCP servers.
Python
How to Stop Burning Thousands of Dollars on Tokens When Working with AI Agents on Code
jCodeMunch MCP indexes your codebase with tree-sitter and feeds AI agents only the relevant code snippets, cutting token costs by 95–99%.
TypeScript
How to Give AI Agents Long-Term Memory Using Obsidian
How to use Obsidian as a long-term memory store for CLI-based AI coding agents, featuring token optimization and automated note-linking.
JavaScript
A Ready-Made Suite of Financial Tools for AI Agents
A ready-made suite of financial tools for AI agents that transforms Claude Code into a financial assistant with market analysis, social reading, and data provider plugins.
HTML
How to Train AI to Write Proper Documents Instead of Fluff
Turn vague AI prompts into professional documents with 700+ ready-made Markdown instructions for engineers, lawyers, and marketers.
JavaScript
How to Clean Text from AI-Generated Clichés Using avoid-ai-writing
A guide to using avoid-ai-writing, an open-source tool that removes AI-generated clichés from text generated by language models.
Python
Your Personal AI Agent on a Short Leash
nanobot is an open-source AI agent engine that runs locally, supports Telegram/Discord integration, MCP tools, and long-term memory without sending data to the cloud.
Unknown
How to Teach an AI Assistant to Understand Azure as Well as a Solutions Architect
Microsoft's Agent-Skills repository offers nearly 200 structured prompts that help AI assistants like Copilot and Claude Code work accurately with Azure services.
Python
How to Stop Feeding LLMs and Teach Agents to Understand Your Code
I tried Memtrace — a tool that turns your codebase into a knowledge graph for AI agents, indexing 15,000 files in 1.5 seconds without LLM calls.
JavaScript
Playwright Skill for Claude Code: When Your AI Assistant Masters Browser Automation
A GitHub project that lets Claude Code write and execute Playwright automation on the fly, generating custom scripts from natural language requests with visible browser control.
Python
How to Teach Claude Code to Control an iOS Simulator
A look at ios-simulator-skill: 22 scripts that let Claude Code control an iOS simulator, filter build noise, and interact with apps via Accessibility API.
1,130
Go
How to Make GitHub Actions Write Reports and Analyze Code Using Plain Text
GitHub's Agentic Workflows let you describe CI/CD tasks in plain Markdown, and AI agents handle the rest. Here's how it works and why it matters.
4,706
C
How to Make an AI Agent Work with a Massive Legacy Codebase Without Losing Context or Money
Discover how to make AI agents work with massive legacy codebases without losing context or burning through your token budget. A deep dive into codebase-emory-mcp.
16,677