Awesome AI Agent Tools
by
Curated catalog of installable components—skills, MCP servers, agent loops, subagents, hooks, plugins, prompts, and CLI tools—that extend and orchestrate AI coding assistants such as Claude Code, Cursor, Codex, Gemini CLI, and dozens of others.
Awesome AI Agent Tools Overview
What is Awesome AI Agent Tools about?
Awesome AI Agent Tools aggregates 678 ready‑to‑install components across eight major categories. Each entry originates from a real open‑source project and is indexed in machine‑readable catalog.json files, enabling programmatic discovery and integration.
How to use Awesome AI Agent Tools?
- Browse the catalog – Navigate the repository folders (
skills/,mcps/,loops/, etc.) or open the correspondingcatalog.jsonfiles to locate a component. - Install – Most components are distributed as npm packages, Docker images, or simple scripts. Follow the installation instructions in the component’s own README (e.g.,
npm install <package>ornpx <package>). - Configure – For MCP servers, add the required environment variables (API keys, endpoints) as documented by the server’s repo.
- Integrate – Import the skill, hook, or plugin into your AI coding assistant configuration (Claude Code
settings.json, Cursor extensions, etc.). - Run – Invoke the new capability through the assistant’s CLI or UI.
Key Features
- Comprehensive coverage: 102 skills, 178 MCP servers, 104 agent loops, 32 subagents, 26 hooks, 59 plugins, 86 prompts, and 91 tools.
- Categorized indexing: Each component is grouped by functional domain (e.g., DevOps, Security, Design) for easy discovery.
- Cross‑tool compatibility: Works with Claude Code, OpenCode, Codex, Cursor, Gemini CLI, Copilot, and >30 other agents.
- Machine‑readable catalogs: JSON files provide a single source of truth for automation scripts and agents.
- Open‑source provenance: Every entry links back to its original repository, ensuring transparency and up‑to‑date maintenance.
Use Cases
- Automated code review – Install the Senior Code Reviewer prompt or corresponding hook to add security and performance checks to every PR.
- End‑to‑end development loops – Deploy an Alpha Loop or Daily Triage Pattern to orchestrate planning, building, testing, and shipping automatically.
- Browser automation – Use the Browser Use MCP to let agents navigate websites, fill forms, and scrape data without manual intervention.
- Skill marketplace – Enable agents to discover and install new capabilities on‑the‑fly via the Find Skills skill.
- CI/CD augmentation – Combine DevOps skills and MCP servers (e.g., Netdata MCP) to monitor and react to infrastructure changes during deployments.
FAQ
Q: Do I need to install all 678 components? A: No. The catalog is a discovery hub; you only install the pieces that match your workflow.
Q: How are the components kept up‑to‑date? A: Each entry points to its upstream open‑source repo, which is periodically synced via CI workflows.
Q: Can I contribute my own tool?
A: Yes. Fork the repo, add a new entry to the appropriate catalog.json, run the validation script, and submit a PR.
Q: Are there any runtime dependencies? A: Most components are pure JavaScript/Node packages; some MCP servers require Docker or specific system binaries, documented in their individual READMEs.
Q: How do I programmatically query the catalog?
A: The JSON files can be loaded directly or accessed via the repository’s raw URLs; you can also use the provided catalog.json index to filter by category or tag.
Awesome AI Agent Tools's README
Awesome AI Agent Tools
Skills, MCP servers, agent workflows, subagents, hooks, plugins, prompts, and CLI tools for AI coding assistants.
678 installable components across 8 categories. Every entry is sourced from a real open-source project. Works with Claude Code, OpenCode, Codex, Cursor, Gemini CLI, Copilot, and 30+ AI coding assistants.
Contents
Skills
102 skills across 9 categories: Development (34) · Productivity (18) · Design (11) · Content (10) · DevOps (9) · Testing (6) · Marketing (6) · Data (5) · Security (3)
Browse all 102 skills in skills/ · catalog.json
Top 5 shown:
| Name | Description | Source |
|---|---|---|
| Executing Plans | Executes implementation plans with verification at each step. | obra/superpowers |
| Frontend Design | Creates distinctive, production-grade frontend interfaces with high design quality. | anthropics/skills |
| Grill Me | Get relentlessly interviewed about a plan or design until every branch of the decision tree is resolved. | mattpocock/skills |
| Vercel React Best Practices | React and Next.js performance optimization guidelines from Vercel Engineering. 40+ rules across 8 categories. | vercel-labs/agent-skills |
| Find Skills | Discover and install new skills for your agent. | vercel-labs/skills |
MCPs
178 mcps across 19 categories: Developer Tools (23) · Search (16) · Research & Data (16) · AI & Machine Learning (15) · Agent Orchestration (15) · Communication (13) · Databases (10) · Marketing (10) · Security (10) · DevOps (8) · Browser Automation (7) · Monitoring (7) · Official Reference (6) · Finance (6) · Cloud Platforms (5) · Blockchain (5) · Design (3) · Mobile (2) · Data Engineering (1)
Browse all 178 mcps in mcps/ · catalog.json
Top 5 shown:
| Name | Description | Source |
|---|---|---|
| n8n MCP | Fair-code workflow automation platform with native AI capabilities and 400+ integrations | n8n-io/n8n |
| MarkItDown | Converts PDF, Office, HTML and image files into clean Markdown for AI consumption | microsoft/markitdown |
| Browser Use MCP | AI-powered browser automation with 100K+ stars. Enables agents to browse the web, fill forms, extract data, and interact with web pages autonomously. | browser-use/browser-use |
| Filesystem MCP | Secure file read/write/list/search operations with configurable directory access controls | modelcontextprotocol/servers |
| Netdata MCP | Real-time infrastructure monitoring with MCP integration for system metrics | netdata/netdata |
Agent Loops
104 loops across 7 categories: engineering (53) · multi-agent (14) · evaluation (12) · meta (10) · operations (6) · design (6) · content (3)
Browse all 104 loops in loops/ · catalog.json
Top 5 shown:
| Name | Description | Source |
|---|---|---|
| The docs sweep | Keeps documentation aligned with the current codebase | Forward-Future/loopy |
| Daily Triage Pattern | 1d-2h maintenance loop for triaging issues, PRs, and priorities | cobusgreyling/loop-engineering |
| Issue Burn-Down Line | Curated backlog through worker, QA, and checkpoint stations | rohanbalkondekar/agent-loop-patterns |
| Alpha Loop | Agent-agnostic automated development loop: Plan -> Build -> Test -> Review -> Ship | bradtaylorsf/alpha-loop |
| The Workflow Loop | Complete shipping loop for coding agents with Plan/Execute/Land/Learn phases | iKon85/agent-workflow-kit |
Subagents
32 subagents across 5 categories: Subagent Collection (16) · Agent Harness (6) · Official SDK (4) · Platform Format (4) · Curated Directory (2)
Browse all 32 subagents in subagents/ · catalog.json
Top 5 shown:
| Name | Description | Source |
|---|---|---|
| oh-my-openagent | Agent harness with async subagent orchestration. Manages subagent delegation, parallel execution, and result aggregation across multiple agent personas. | code-yeongyu/oh-my-openagent |
| Microsoft Agent Framework | Microsoft's comprehensive framework for building autonomous AI agents with multi-agent patterns, Azure integration, and .NET/Python support. | learn.microsoft.com |
| awesome-claude-code | Ecosystem directory indexing 47K+ stars of Claude Code resources including subagent collections, skills, MCP servers, and community extensions. | hesreallyhim/awesome-claude-code |
| awesome-claude-code-subagents | Curated list of 154+ Claude Code subagent definitions including code-reviewer, debugger, test-writer, planner, and more. VoltAgent's definitive collection of reusable agent personas. | VoltAgent/awesome-claude-code-subagents |
| oh-my-codex | Codex orchestration harness with 33 agent prompts. Manages subagent lifecycle, handoffs, and coordinated task execution for Codex CLI. | Yeachan-Heo/oh-my-codex |
Hooks
26 hooks across 7 categories: Security (6) · Session Management (5) · Automation (4) · Quality (3) · Safety (3) · Utility (3) · Notifications (2)
Browse all 26 hooks in hooks/ · catalog.json
Top 5 shown:
| Name | Description | Source |
|---|---|---|
| Secret Scanner | Scans for leaked secrets (API keys, tokens, passwords) before writing or editing files | rohitg00/awesome-claude-code-toolkit |
| Block Dangerous Commands | Blocks rm -rf, fork bombs, curl|sh, and other destructive shell commands | karanb192/claude-code-hooks |
| Lasso Security Prompt Injection Defenses | Enterprise-grade prompt injection detection and prevention hooks for Claude Code. Detects and blocks indirect prompt injection attacks via tool outputs. | lasso-security/claude-hooks |
| awesome-claude-code-hooks | Curated directory of Claude Code hooks organized by category. Meta-resource for discovering hooks in the ecosystem. | ithiria894/awesome-claude-code-hooks |
| BountyGuard Pre-Task Audit | Pre-task security hook that audits GitHub bounty issues for verified escrow locks and prompt-injection payloads before an agent writes code | doomsday-network/bounty-guard |
Plugins
59 plugins across 11 categories: Claude Code (16) · OpenCode (9) · Cross-Tool (9) · VS Code AI (6) · Cursor (5) · Windsurf (4) · JetBrains (4) · Copilot (3) · Aider (1) · Codex (1) · Hermes Agent (1)
Browse all 59 plugins in plugins/ · catalog.json
Top 5 shown:
| Name | Description | Source |
|---|---|---|
| Superpowers Plugin | Comprehensive skill pack with 60+ pre-built skills for Claude Code workflows | superpowers.dev |
| Official Claude Code Marketplace | Official marketplace for Claude Code plugins with 255+ community-contributed extensions | claude.ai |
| Awesome CursorRules | Curated collection of cursor rules by PatrickJS with 20K stars | PatrickJS/awesome-cursorrules |
| AgentEnv | Project-scoped AI agent and plugin environment manager. Manages agent configurations across multiple AI coding tools. | kvcache-ai/AgentENV |
| Oh My Hermes | Hermes Agent workflow plugin with project memory and task-specific model and reasoning routing. | rlaope/oh-my-hermes |
Prompts
86 prompts across 17 categories: Coding (9) · Architecture (8) · Image Generation (8) · General Purpose (7) · DevOps (6) · Code Review (5) · Debugging (5) · Documentation (5) · Reasoning (5) · Security (4) · Testing (4) · Data (4) · Design (4) · Productivity (4) · Agent Workflows (4) · Content (3) · Marketplace (1)
Browse all 86 prompts in prompts/ · catalog.json
Top 5 shown:
| Name | Description | Source |
|---|---|---|
| Senior Code Reviewer | Thorough code review with security, performance, and maintainability analysis | f/prompts.chat |
| Prompt Engineer | Meta-prompt for designing and optimizing other prompts | dair-ai/Prompt-Engineering-Guide |
| Craft Code Refactor | Systematic code improvement with test coverage maintenance | hoangatg/awesome-ai-prompts-2026 |
| SQL Query Optimizer | Analyze and optimize SQL queries with index suggestions | openai/openai-cookbook |
| Image Generation Prompt Crafter | Craft detailed prompts for DALL-E, Midjourney, and Flux | Ryan-yang125/gpt-image-2-prompts |
Tools
91 tools across 14 categories: AI Coding CLIs (15) · Code Analysis (13) · Cloud & DevOps (7) · Formatting & Linting (7) · Agent Training & Eval (7) · Git Utilities (6) · API Testing (6) · Package Managers (5) · Docker & Containers (5) · Monitoring (5) · Agent Memory (4) · Database CLIs (4) · Terminal Enhancement (4) · AI APIs (3)
Browse all 91 tools in tools/ · catalog.json
Top 5 shown:
| Name | Description | Source |
|---|---|---|
| Ollama | Run LLMs locally. Llama, Mistral, Phi, Gemma, and more. | ollama/ollama |
| Gemini CLI | Google's AI coding agent in the terminal. | google-gemini/gemini-cli |
| Claude Code | Anthropic's agentic coding tool. Terminal-native AI pair programmer. | anthropics/claude-code |
| Bun | Incredibly fast JavaScript runtime, bundler, and package manager. | oven-sh/bun |
| Netdata | Real-time performance and health monitoring. | netdata/netdata |
Contributing
We welcome contributions. You can:
- Manual PR - fork, add an entry to a
catalog.jsonfile, validate, and submit. See contributing.md. - Agent-automated - give your AI agent the contributing.md guide and it handles everything.
- Open an issue to suggest a tool we should add.
All data comes from catalog.json files in each folder. These catalogs are the single source of truth for programmatic discovery.
Awesome AI Agent Tools Reviews
Login Required
Please log in to share your review and rating for this MCP.
Similar MCP Servers like Awesome AI Agent Tools
Explore related MCPs that share similar capabilities and solve comparable challenges
Headroom
by headroomlabs-ai
Compress tool outputs, logs, files, RAG chunks, and conversation history before they reach the LLM, keeping answers identical while saving up to 95% of tokens for JSON payloads.
Git
Officialby modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
Zed
OfficialClientby zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
Everything
Officialby modelcontextprotocol
Model Context Protocol Servers
Time
Officialby modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
Cline
OfficialClientby cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
Context7 MCP
Officialby upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
Daytona
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.
Continue
OfficialClientby continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.