Theo dõi tốc độ tăng trưởng và hoạt động, không chỉ tổng số stars.
Agent tooling for generative LEGO models building, built with Astra and Opus 5.5, powered by Jev
AI coding spend management for engineering teams. Track Cursor, Claude Code, Codex, Copilot, usage, cost, plan utilization, seat waste, and device health.
Breakthrough Method for Agile Ai Driven Development
Open-source long-term, time-aware memory engine for AI agents (MCP + hybrid search + bi-temporal recall)
Durable execution framework for AI agents in Go. Keeps agent state, tool calls, and execution loops resilient across process crashes.
Fight spam by generating and sending a fake "user unknown" bounce emails
A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.
Security help for defenders: grade your site's security headers (fixes + README badge) and read logs/code to find what happened. Claude Code plugin, MCP server, no install.
OpenShell is the safe, private runtime for autonomous AI agents.
WSP MCP - Free WordPress MCP For Connecting AI Coding Agents
Local AI image generation for Mac. Run Qwen-Image 2.1 on Apple Silicon, offline and private, with a built-in MCP server for Claude Code and AI agents.
A terminal for AI CLIs, expanded into a rich visual workspace for each session. Claude Code, Codex, Cursor CLI, and more. macOS and Windows/WSL. Extend it further and share your additions.
🏆 Ranked list of 167 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.
The axis of agent knowledge. Auto-generates and keeps in sync AGENTS.md, CLAUDE.md, .cursorrules — context files that AI agents read.
A minimal, composable Go library for building agentic tool-calling loops
Open-source Agent Skill that finds and removes AI slop from your writing
Read the omens before you `curl | sh`: explains what an install script will do before it runs, and stops AI coding agents running unreviewed installers (Claude Code hook).
Open source library for N64 development.
Plataforma de Aceleração Computacional (PAC)
The Express Edition
Enterprise-grade, text-based blueprint designed to fix formatting crashes, eliminate semantic bleed, and purify raw B2B data before it enters AI engines
Can a model that only picks from a list learn to talk? JEV types every reply one key at a time.