DEV Community

Deduped profile picture

Deduped

Deduped tracks the hottest AI repos on GitHub and shows exactly how to use them: step-by-step use cases, copy-paste agent prompts, and real builds from people using them.

Joined Joined on  Personal website https://dedupedai.com
How to cut Claude Code token use by up to 90% with RTK (setup in 10 minutes)

How to cut Claude Code token use by up to 90% with RTK (setup in 10 minutes)

Comments
4 min read
How to make a product launch video with Claude Code and HyperFrames (HTML to MP4)

How to make a product launch video with Claude Code and HyperFrames (HTML to MP4)

1
Comments
4 min read
How to debloat a slow Google TV over Wi-Fi with Claude Code (and undo it)

How to debloat a slow Google TV over Wi-Fi with Claude Code (and undo it)

Comments
4 min read
How to reverse engineer an app feature with your coding agent using REA (MCP)

How to reverse engineer an app feature with your coding agent using REA (MCP)

Comments
4 min read
TrenTorch: learn ML by building your own framework in NumPy (and 350+ browser questions)

TrenTorch: learn ML by building your own framework in NumPy (and 350+ browser questions)

Comments
4 min read
Claude Flightdeck: a live dashboard for Claude Code context, cost, permissions and subagents

Claude Flightdeck: a live dashboard for Claude Code context, cost, permissions and subagents

Comments
4 min read
How to install Free My TV: an ad-free home screen for Google TV, LG webOS and Samsung

How to install Free My TV: an ad-free home screen for Google TV, LG webOS and Samsung

Comments
5 min read
How to run local LLMs with Ollama and plug them into your coding agent

How to run local LLMs with Ollama and plug them into your coding agent

Comments
3 min read
How to give Claude Code a web scraping tool with Crawl4AI (MCP)

How to give Claude Code a web scraping tool with Crawl4AI (MCP)

Comments
3 min read
How to serve an OpenAI-compatible local API with llama.cpp

How to serve an OpenAI-compatible local API with llama.cpp

Comments
4 min read
RTX 4090 "2x FP16" unlock: real GEMM gains are 12 to 34%. How to test it safely

RTX 4090 "2x FP16" unlock: real GEMM gains are 12 to 34%. How to test it safely

Comments
4 min read
How to share memory between Claude Code, Codex and Cursor with Beacon

How to share memory between Claude Code, Codex and Cursor with Beacon

Comments
4 min read
How to add Solid Glass to a shadcn/ui app, plus ready-made AI agent components

How to add Solid Glass to a shadcn/ui app, plus ready-made AI agent components

Comments 1
3 min read
How to run DeepSeek's DeepInfer: build, deterministic outputs and JSON schema

How to run DeepSeek's DeepInfer: build, deterministic outputs and JSON schema

Comments
3 min read
How to give your coding agent ears with earshot (CPU-only MCP server)

How to give your coding agent ears with earshot (CPU-only MCP server)

Comments
3 min read
How to strip the ads off an Android or Google TV in 15 minutes with a coding agent

How to strip the ads off an Android or Google TV in 15 minutes with a coding agent

Comments
3 min read
How to give an AI agent a real iPhone with a $7 ESP32

How to give an AI agent a real iPhone with a $7 ESP32

Comments
4 min read
5 hot GitHub repos this week and exactly how to use them

5 hot GitHub repos this week and exactly how to use them

Comments
4 min read
loading...