35 packages found
RootCause is a local-first MCP server that turns natural-language requests into evidence-backed incident analysis, Kuber
Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to i
AI memory brain for Claude Code, Cursor, Copilot & Windsurf — 120+ MCP tools. Persistent sessions, lessons learned, sema
An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, L
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MC
Opinionated, repo-local configuration for GitHub Copilot (Chat + Agent mode): instruction hierarchy, reusable prompt fil
CLI-first API testing tool. YAML-defined tests, structured JSON output, built for AI-assisted workflows.
One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, a
Hand off tasks to Devin — a plugin/skill for Claude Code, Codex, Cursor, and any coding agent
Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, usi
Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over
A curated collection of high-quality prompt templates designed for Claude, focused on coding, problem-solving, productiv
A collection of production-ready slash commands for Claude Code
18 mental models and critical thinking frameworks for Claude Code - First Principles, Bayesian, Systems Thinking, OODA,
Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best pract
gitctx is an MCP server that gives agents and IDE assistants targeted, up-to-date access to GitHub repositories. Open-so
The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and busine
Multi-cloud cost management MCP server (Azure + GCP). Read-only access to spending, anomalies, forecasts, budgets, and g
Production-extracted architecture for Claude Code CLI. 3-layer system: CLAUDE.md constitution + specialist Skills + pers
Open, audit-grade agentic data quality framework with portable industry packs
AI 測試大師 — MCP server driving pytest / Jest / Cypress / Go / Maestro. Analyze, generate, run, advise. Web + Mobile (iOS/A
Context infrastructure for AI-assisted development — on-demand Obsidian vault access via MCP
A MCP server that bridges TestDino with AI agents such as Cursor and Claude. Navigate test results, analyze failures, an
Deterministic LLM prompt defense scanner — 12 attack vectors, pure regex, zero AI cost, < 5ms
A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversaria
Claude Code plugin that stops "almost done" loops — declare your stages in workflow.json, runs them as a state machine t
Distilled decision-making frameworks from Garry Tan's gstack, packaged as 7 focused Agent Skills.
Turn ad-hoc Claude Code / Codex / Cursor sessions into a repeatable loop — research → plan → wave-execute → close. Paral
From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration.
How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforce
A curated system of production-ready Claude Code skills with quantitative evaluation reports, golden test fixtures, and
@microsoft✓ OfficialGift your VS Code agent a real debugger: breakpoints, stepping, inspection.
NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust
obra/superpowers extended — 14→24 skills, 6 GadaaLabs engineering improvements, override infrastructure, one-command ins