Popular AI Agents — Trust Ranked
Top 50 AI agents by Nerq Trust Score. Updated continuously from 204K+ indexed agents across GitHub, npm, PyPI, HuggingFace, and MCP registries.
| # | Agent | Grade | Score | Category | Stars | Downloads | Source |
|---|---|---|---|---|---|---|---|
| 1 | IBM/mcp-context-forge A Model Context Protocol (MCP) Gateway & Registry. Serves as a central management point for tools, r |
A | 86.4 | infrastructure | 3,477 | — | github |
| 2 | mikeyobrien/ralph-orchestrator An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration. |
A | 85.0 | infrastructure | 2,379 | — | github |
| 3 | tech-leads-club/agent-skills Secure, validated skill registry for professional AI coding agents. |
A | 83.6 | coding | 1,573 | — | github |
| 4 | snyk/agent-scan Security scanner for AI agents, MCP servers and agent skills. |
A | 83.5 | infrastructure | 1,981 | — | github |
| 5 | livekit/agents-js Build realtime multimodal AI agents with Node.js |
A | 82.8 | coding | 790 | — | github |
| 6 | vstorm-co/full-stack-fastapi-nextjs-llm-template Full-stack template for AI/LLM apps: FastAPI backend + Next.js frontend, optimized for PydanticAI, L |
A | 82.2 | infrastructure | 585 | — | github |
| 7 | promptfoo/promptfoo Test and evaluate LLMs for security vulnerabilities. |
A | 82.0 | security | 18,373 | — | github |
| 8 | TencentCloudBase/CloudBase-MCP CloudBase MCP - Connect CloudBase to your AI Agent. Go from AI prompt to live app. |
A | 82.0 | infrastructure | 980 | — | github |
| 9 | SmythOS/sre The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure |
A | 81.9 | infrastructure | 1,232 | — | github |
| 10 | microsoft/qlib Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, |
A | 81.8 | finance | 37,615 | — | github |
| 11 | Giskard-AI/giskard-oss 🐢 Open-Source Evaluation & Testing library for LLM Agents |
A | 81.6 | AI tool | 5,122 | — | github |
| 12 | nanoclaw A lightweight AI assistant for secure containerized operations on WhatsApp. |
A | 81.5 | communication | 6,874 | — | github |
| 13 | nanoclaw A lightweight, containerized AI assistant for WhatsApp with memory and scheduling capabilities. |
A | 81.5 | communication | 7,735 | — | github |
| 14 | zylos-ai/zylos-core Open-source agent infrastructure for team collaboration. |
A | 81.4 | infrastructure | 798 | — | github |
| 15 | numtide/llm-agents.nix Nix packages for AI coding agents and development tools. |
A | 81.3 | coding | 903 | — | github |
| 16 | stacklok/toolhive ToolHive makes deploying MCP servers easy, secure and fun |
A | 81.1 | infrastructure | 1,610 | — | github |
| 17 | badlogic/pi-mono An AI agent toolkit for CLI coding with unified LLM API and various UIs. |
A | 80.9 | coding | 27,925 | — | github |
| 18 | ComposioHQ/composio Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed wor |
A | 80.9 | infrastructure | 27,590 | — | github |
| 19 | callstackincubator/agent-device CLI for UI automation on iOS, tvOS, macOS, Android, and AndroidTV. |
A | 80.5 | devops | 1,241 | — | github |
| 20 | williamzujkowski/strudel-mcp-server A Model Context Protocol (MCP) server that gives Claude direct control over Strudel.cc for AI-assist |
A | 80.3 | infrastructure | 158 | — | github |
| 21 | ccmanager CLI application for managing multiple AI coding assistant sessions across projects. |
A | 80.3 | coding | 831 | — | github |
| 22 | vibe-remote Your AI agent army for coding, commanded from Slack, Discord, WeChat & Lark. |
A | 80.2 | coding | 361 | — | github |
| 23 | modelcontextprotocol/java-sdk The official Java SDK for Model Context Protocol servers and clients. Maintained in collaboration wi |
A | 80.1 | infrastructure | 3,216 | — | github |
| 24 | AIPex AIPex automates browser tasks and manages tab history efficiently. |
A | 80.1 | coding | 1,124 | — | github |
| 25 | pydantic/pydantic-ai GenAI Agent Framework for building autonomous AI assistants. |
A | 80.0 | coding | 15,825 | — | github |
| 26 | langchain-ai/langgraphjs Framework to build resilient language agents as graphs. |
B | 79.9 | coding | 2,559 | — | github |
| 27 | a2aproject/a2a-samples Samples using the Agent2Agent (A2A) Protocol |
B | 79.9 | infrastructure | 1,339 | — | github |
| 28 | camel-ai/camel 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://ww |
B | 79.7 | research | 16,069 | — | github |
| 29 | OpenDCAI/Paper2Any Converts text and topics into research figures, technical route diagrams, and presentation slides. |
B | 79.7 | research | 1,698 | — | github |
| 30 | microsoft/azure-devops-mcp The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents. |
B | 79.7 | devops | 1,291 | — | github |
| 31 | inclusionAI/AReaL Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible. |
B | 79.7 | research | 3,558 | — | github |
| 32 | hiyouga/LlamaFactory Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) |
B | 79.7 | research | 67,794 | — | github |
| 33 | raptor Raptor is an autonomous security research framework for advanced security operations and research. |
B | 79.6 | security | 1,095 | — | github |
| 34 | DLR-RM/rl-baselines3-zoo A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimi |
B | 79.6 | research | 2,725 | — | github |
| 35 | opal OPAL is an open policy administration layer for managing and distributing policies in real-time. |
B | 79.6 | infrastructure | 5,422 | — | github |
| 36 | pydantic/logfire AI observability platform for production LLM and agent systems. |
B | 79.5 | infrastructure | 4,040 | — | github |
| 37 | GoogleCloudPlatform/agent-starter-pack Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/C |
B | 79.5 | devops | 5,761 | — | github |
| 38 | samples A collection of samples for building AI agents using the Strands Agents SDK. |
B | 79.5 | infrastructure | 638 | — | github |
| 39 | laravel/mcp Rapidly build MCP servers for your Laravel applications. |
B | 79.4 | devops | 679 | — | github |
| 40 | agentscope-ai/agentscope AgentScope is a production-ready, easy-to-use agent framework with essential abstractions that work |
B | 79.3 | infrastructure | 16,400 | — | github |
| 41 | livekit/agents A framework for building realtime voice AI agents 🤖🎙️📹 |
B | 79.3 | coding | 9,398 | — | github |
| 42 | a2aproject/a2a-python Official Python SDK for the Agent2Agent (A2A) Protocol |
B | 79.3 | infrastructure | 1,676 | — | github |
| 43 | run-llama/llama_index LlamaIndex is the leading document agent and OCR platform |
B | 79.3 | coding | 47,102 | — | github |
| 44 | wshobson/agents Intelligent automation and multi-agent orchestration for Claude Code |
B | 79.3 | devops | 29,146 | — | github |
| 45 | agentgateway/agentgateway Next Generation Agentic Proxy for AI Agents and MCP servers |
B | 79.2 | coding | 1,777 | — | github |
| 46 | alibaba/nacos an easy-to-use dynamic service discovery, configuration and service management platform for building |
B | 79.1 | infrastructure | 32,669 | — | github |
| 47 | mcp-scan Security scanner for AI agents, MCP servers, and agent skills to detect vulnerabilities and prompt i |
B | 79.1 | security | 1,460 | — | github |
| 48 | aidlc-workflows AI-DLC is an intelligent software development workflow that adapts to your needs. |
B | 79.0 | devops | 911 | — | github |
| 49 | truera/trulens Evaluation and Tracking for LLM Experiments and AI Agents |
B | 78.9 | research | 3,101 | — | github |
| 50 | InsForge/InsForge AI-native backend platforms, turn coding agents into fullstack builders. |
B | 78.9 | infrastructure | 1,466 | — | github |
Scores recalculated daily. Trust Score methodology · Try the API · Add a trust badge
Frequently Asked Questions
What are the most popular AI agents?
The most popular AI agents by trust score include frameworks like LangChain, CrewAI, AutoGen, and tools like SWE-agent. Nerq indexes 204K+ agents from GitHub, npm, PyPI, HuggingFace, and MCP registries with independent Trust Scores.
How are AI agent trust scores calculated?
Nerq Trust Scores (0-100) are calculated across 5 dimensions: Code Quality (25%), Community Adoption (25%), Compliance (20%), Operational Health (15%), and Security (15%). Security scoring includes CVE data from the GitHub Advisory Database.
What is an AI agent?
An AI agent is an autonomous software system that can perceive its environment, make decisions, and take actions to achieve goals. Unlike simple chatbots, agents can use tools, chain reasoning steps, and interact with external systems.
How many AI agents exist?
Nerq indexes over 204,000 AI agents and MCP servers from 6 ecosystems: GitHub, npm, PyPI, HuggingFace, MCP registries, and Docker Hub. The number is growing rapidly as the agentic economy accelerates.