Theo dõi tốc độ tăng trưởng và hoạt động, không chỉ tổng số stars.
A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync everywhere”.
Reproducible code and frozen inputs for the AI-written movie review detection experiment
Native macOS database client
A Lighthouse for your AI agent stack — measures the real token cost of MCP servers, skills, and rules; flags security issues and duplicates; grades your setup A-F.
QEP's (QGIS Enhancement Proposals) are used in the process of creating and discussing new enhancements for QGIS
AI-driven security engagements with specialist agents, a Kali runtime, and durable orchestration.
A voice-controlled toy car: a phone rides on it and drives an FT232H over WebUSB in FTDI async bitbang mode.
It should be impossible for AI to make a bad UI.
a tiny ram for your RAM 🐏
120 patterns that make writing read like AI slop, with an agent skill for Claude Code and Codex.
A YouTube transcript CLI built for humans and AI agents.
Persistent, forkable workspaces for AI agents. Git-aware snapshots, verified resets, and control over what survives across sessions.
The Agentic-Native Operating System
Trace which Claude Code or OpenCode configuration value actually wins - offline, read-only, and with every redaction and coverage gap stated.
AI that makes sure devs understand what they've vibe coded
A design pack that turns a frontier AI into an architect for multi-agent systems.
Hackathon demo: a usefulness and pricing layer for AI agents on top of Keenable search (prices simulated)
A browser-based document anonymizer that strips PII before sharing with AI services and restores original names in responses. No server, no API calls - everything runs locally via WebAssembly.
Transparent anonymization proxy for AI-assisted pentesting. Strips IPs, credentials, hostnames and PII before they reach any LLM (Claude, OpenAI, OpenRouter). Local Ollama + regex detection. Per-engagement vault.
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
A voice assistant with a face for the Windows desktop. Works with any AI model: OpenAI, Claude, Gemini, OpenRouter, Groq or local Ollama.