Tag
#GitHub
22 posts
MoneyPrinterV2: What 18,000 Stars Worth of Automated Content Actually Looks Like
An assembly line for AI content — local LLMs write the script, KittenTTS reads it, Gemini paints the pictures. The video uploads itself.
Project N.O.M.A.D.: The Knowledge Bunker You Build for a Rainless Day
When the cloud evaporates, what stays on your disk matters.
ruanyf/weekly: The Digital Lighthouse in a Sea of Algorithmic Slop
At the end of the infinite scroll, one man is still standing.
Superpowers: The Workflow That Teaches AI Agents Discipline
Superpowers makes coding agents slow down, ask questions, write plans, and test first. The result is less flashy AI code, but much more trustworthy code.
The Agency: Transform Your Workflow with a Team of AI Specialists
Discover how The Agency replaces generic prompts with a meticulously crafted roster of specialized AI agents for engineering, design, and more.
BitNet: The Era of 1-bit LLMs is Finally Here
Explore bitnet.cpp, Microsoft's official framework for 1-bit LLMs that replaces multiplications with additions for massive speedups.
Lightpanda: The Zero-Bloat Headless Browser Built in Zig
Discover Lightpanda, a headless browser built from scratch in Zig for ultra-fast AI agents and automation without the overhead of Chromium.
MiroFish: Rehearsing the Future in an AI Social Sandbox
Discover MiroFish, a universal swarm intelligence engine that uses multi-agent simulations to predict future trajectories in a digital mirror world.
Defuddle: The Next Generation of Web Content Extraction
Defuddle is an emerging TypeScript alternative to Mozilla Readability. Written for the Obsidian Web Clipper, it extracts clean HTML for markdown conversion, with custom site extractors and math/code block standardization.
Khoj: The Open-Source AI Second Brain You Can Self-Host
Khoj is an open-source personal AI app that acts as your AI second brain — chat with any LLM, search your documents with semantic AI, build custom agents, and self-host it completely on your own machine.
OpenSandbox: The Universal Sandbox Platform Every AI Agent Needs
Alibaba open-sourced a general-purpose sandbox platform for AI applications — supporting Coding Agents, GUI Agents, RL Training and more, with multi-language SDKs and Docker/Kubernetes runtimes.
Stop Context Rot: How Get Shit Done Powers the Ultimate 10x Agentic Engine
A deep dive into GSD (Get Shit Done), a powerful meta-prompting and context-engineering system that averts AI context rot for Claude, Gemini, and general AI agents.
Context Engineering: The Discipline That Separates Good AI Agents from Great Ones
A deep dive into Agent Skills for Context Engineering — the open-source toolkit cited in academic research that teaches you how to curate context windows like a professional AI engineer.
Awesome OpenClaw: From Generic AI to a Team of Autonomous Employees
Discover real-world use cases for OpenClaw that turn a simple chat interface into a proactive, self-healing, and goal-driven autonomous workforce.
Unleashing the Super Agent Harness: A Deep Dive into Bytedance's DeerFlow
Discover how DeerFlow 2.0 transforms from a deep research tool into a full-fledged agent harness with sandboxing, sub-agents, and persistent memory.
GitNexus: The Knowledge Graph That Makes AI Agents Actually Understand Your Codebase
GitNexus indexes any codebase into a knowledge graph — every dependency, call chain, cluster, and execution flow — then exposes it through MCP tools so AI agents never miss code.
Inside the Black Box: What Leaked AI System Prompts Reveal About How Your Favorite Tools Actually Think
A deep-dive into the most comprehensive collection of leaked system prompts from Cursor, Manus, Windsurf, Devin, v0, and 30+ other AI tools — revealing their core architectures, tool designs, and agent philosophies.
OpenBB Explained: The Open Data Platform for Investment Research
A deep dive into OpenBB, the open-source platform that unifies financial data APIs into a single interface for Python developers, analysts, and AI agents.
OpenClaw: Your Personal AI Assistant Across Every Channel
A deep dive into OpenClaw, a self-hosted personal AI assistant that unifies WhatsApp, Telegram, Slack, Discord, Signal, iMessage, and more under a single local-first gateway.
PentAGI Explained: Auto-Hacking with Multi-Agent AI
A deep dive into PentAGI, an autonomous AI-driven penetration testing system combining 20+ security tools with a smart multi-agent architecture.
Pi Mono Explained: The Anti-Framework for AI Coding Agents
A deep dive into Pi Mono, the radically extensible monorepo for building AI agents that refuses to dictate your workflow—and lets you build the agent you actually want.
Shannon Explained: The Autonomous AI Pentester That Breaks Your App Before Hackers Do
A deep dive into Shannon, the fully autonomous AI penetration tester by Keygraph that executes real exploits—not just alerts—using a sophisticated multi-agent architecture.