Popular AI Agents โ 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 | โ | github |
| 2 | 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 | 86.2 | infrastructure | 585 | โ | github |
| 3 | Giskard-AI/giskard-oss ๐ข Open-Source Evaluation & Testing library for LLM Agents |
A | 85.6 | AI tool | 5,122 | โ | github |
| 4 | pydantic/logfire AI observability platform for production LLM and agent systems. |
A | 83.5 | infrastructure | 4,040 | โ | github |
| 5 | snyk/agent-scan Security scanner for AI agents, MCP servers and agent skills. |
A | 83.5 | infrastructure | 1,981 | โ | github |
| 6 | GoogleCloudPlatform/agent-starter-pack Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/C |
A | 83.5 | devops | 5,761 | โ | github |
| 7 | a2aproject/a2a-python Official Python SDK for the Agent2Agent (A2A) Protocol |
A | 83.3 | infrastructure | 1,676 | โ | github |
| 8 | livekit/agents A framework for building realtime voice AI agents ๐ค๐๏ธ๐น |
A | 83.3 | coding | 9,398 | โ | github |
| 9 | alibaba/nacos an easy-to-use dynamic service discovery, configuration and service management platform for building |
A | 83.1 | infrastructure | 32,669 | โ | github |
| 10 | infiniflow/ragflow RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge |
A | 82.9 | infrastructure | 73,683 | โ | github |
| 11 | anomalyco/opencode The open source coding agent. |
A | 82.5 | coding | 108,137 | โ | github |
| 12 | BrainBlend-AI/atomic-agents Building AI agents, atomically |
A | 82.5 | coding | 5,687 | โ | github |
| 13 | topoteretes/cognee Knowledge Engine for AI Agent Memory in 6 lines of code |
A | 82.5 | coding | 12,475 | โ | github |
| 14 | google/adk-js An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated |
A | 82.5 | coding | 824 | โ | github |
| 15 | btriapitsyn/openchamber Desktop and web interface for OpenCode AI agent. |
A | 82.5 | ai_assistant | 1,213 | โ | github |
| 16 | UfoMiao/zcf Zero-Config Code Flow for Claude code & Codex automation. |
A | 82.5 | devops | 5,508 | โ | github |
| 17 | strands-agents/docs Documentation for the Strands Agents SDK. A model-driven approach to building AI agents in just a fe |
A | 82.3 | infrastructure | 175 | โ | github |
| 18 | ZhuLinsen/daily_stock_analysis LLM้ฉฑๅจ็A/H/็พ่กๆบ่ฝๅๆๅจ |
A | 82.2 | finance | 14,541 | โ | github |
| 19 | generalaction/emdash Emdash is the Open-Source Agentic Development Environment (๐งก YC W26). Run multiple coding agents in |
A | 82.2 | coding | 2,247 | โ | github |
| 20 | PromptX PromptX transforms AI agents into industry experts with revolutionary interaction design. |
A | 81.9 | other | 3,570 | โ | github |
| 21 | FunnyWolf/agentic-soc-platform Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operat |
A | 81.7 | security | 579 | โ | github |
| 22 | UnicomAI/wanwu China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent developme |
A | 81.6 | AI tool | 4,104 | โ | github |
| 23 | nanoclaw A lightweight AI assistant for secure containerized operations on WhatsApp. |
A | 81.5 | communication | 6,874 | โ | github |
| 24 | 54yyyu/zotero-mcp Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model |
A | 81.5 | research | 1,461 | โ | github |
| 25 | getsentry/XcodeBuildMCP A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS |
A | 81.4 | infrastructure | 4,530 | โ | github |
| 26 | google/adk-go An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agent |
A | 81.4 | infrastructure | 7,113 | โ | github |
| 27 | runkids/skillshare ๐ Sync skills across all AI CLI tools with one command and simplify team sharing. Supporting Claude |
A | 81.4 | coding | 565 | โ | github |
| 28 | numtide/llm-agents.nix Nix packages for AI coding agents and development tools. |
A | 81.3 | coding | 903 | โ | github |
| 29 | NVIDIA/NeMo-Agent-Toolkit The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing te |
A | 81.3 | infrastructure | 1,878 | โ | github |
| 30 | katanemo/plano Delivery infrastructure for agentic apps - Plano is an AI-native proxy and data plane that offloads |
A | 81.3 | infrastructure | 5,866 | โ | github |
| 31 | dyoshikawa/rulesync A Utility CLI for AI Coding Agents |
A | 81.3 | infrastructure | 907 | โ | github |
| 32 | aws-samples/sample-agentic-frameworks-on-aws Build Agentic AI solutions on AWS, using latest OSS Agentic Frameworks. |
A | 81.3 | agent framework | 234 | โ | github |
| 33 | influxdata/telegraf Agent for collecting, processing, aggregating, and writing metrics, logs, and other arbitrary data. |
A | 81.2 | infrastructure | 16,712 | โ | github |
| 34 | Agent-First-Organization The official Python library for Arklex framework |
A | 81.2 | โ | 693 | โ | github |
| 35 | langchain-ai/langchain The platform for reliable agents. |
A | 81.0 | coding | 127,759 | โ | github |
| 36 | agentset-ai/agentset The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP s |
A | 80.9 | infrastructure | 1,868 | โ | github |
| 37 | MemTensor/MemOS AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory |
A | 80.9 | infrastructure | 5,691 | โ | github |
| 38 | browser-use/browser-use ๐ Make websites accessible for AI agents. Automate tasks online with ease. |
A | 80.9 | coding | 79,962 | โ | github |
| 39 | badlogic/pi-mono An AI agent toolkit for CLI coding with unified LLM API and various UIs. |
A | 80.9 | coding | 27,925 | โ | github |
| 40 | ComposioHQ/composio Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed wor |
A | 80.9 | infrastructure | 27,590 | โ | github |
| 41 | samugit83/redamon An AI-powered agentic red team framework that automates offensive security operations, from reconnai |
A | 80.8 | security | 1,060 | โ | github |
| 42 | callstackincubator/agent-device CLI for UI automation on iOS, tvOS, macOS, Android, and AndroidTV. |
A | 80.5 | devops | 1,241 | โ | github |
| 43 | AndrewAltimit/template-repo Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanis |
A | 80.5 | infrastructure | 110 | โ | github |
| 44 | HumanSignal/Adala Adala: Autonomous DAta (Labeling) Agent framework |
A | 80.5 | data | 1,363 | โ | github |
| 45 | newrelic/node-newrelic New Relic Node.js agent code base. Developers are welcome to create pull requests here, please see o |
A | 80.5 | โ | 997 | โ | github |
| 46 | test-zeus-ai/testzeus-hercules Hercules is an open-source testing agent for automated validations. |
A | 80.5 | devops | 943 | โ | github |
| 47 | MemMachine/MemMachine Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory sto |
A | 80.5 | AI tool | 4,409 | โ | github |
| 48 | jarrodwatts/claude-hud A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and |
A | 80.5 | coding | 3,616 | โ | github |
| 49 | toeverything/AFFiNE There can be more than Notion and Miro. AFFiNE(pronounced [ษโfain]) is a next-gen knowledge base tha |
A- | 80.5 | AI tool | 63,105 | โ | github |
| 50 | groupultra/telegram-search ๐ ๅฏผๅบๅนถๆจก็ณๆ็ดข Telegram ่ๅคฉ่ฎฐๅฝ | Export and fuzzy search your Telegram chat history |
A | 80.4 | infrastructure | 3,785 | โ | 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.