AI Trust Registry for open-source AI agent projects.
Independent trust scores for 1387 open-source AI agent projects and 396 agent skills, every point from public, checkable signals. How scoring works →
Your tracked agents
Changes since your last visit show up here.
Track agents with the ★ button — their score, grade, and rank changes show up here on your next visit. Sign in to sync across devices and get alerts.
| #↑ | Δ | Agent | Grade | Stars | Last Push | Commits | HVTrust |
|---|---|---|---|---|---|---|---|
| 1 | = | deepset-ai/haystack Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search… | A | 27.0k |
2026-11-14
|
279 | 96.4 was 95.9 ▲0.1 |
| 2 | = | vercel/ai The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents | A | 28.0k |
2026-11-14
|
596 | 94.6 was 92.3 ▼0.2 |
| 3 | = | langchain-ai/langgraph Build resilient agents. | A | 45.0k |
2026-11-15
|
134 | 94.5 was 93.9 — |
| =4 | = | openai/openai-agents-js A lightweight, powerful framework for multi-agent workflows and voice agents | A | 4.0k |
2026-11-15
|
48 | 93.2 was 92.6 — |
| =4 | = | modelcontextprotocol/typescript-sdk The official TypeScript SDK for Model Context Protocol servers and clients | A | 13.8k |
2026-11-10
|
18 | 93.2 was 90.3 ▼0.2 |
| =6 | = | modelcontextprotocol/python-sdk The official Python SDK for Model Context Protocol servers and clients | A | 24.9k |
2026-11-05
|
11 | 92.9 was 90.7 ▼1.0 |
| =6 | = | promptfoo/promptfoo Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic. | A | 27.2k |
2026-11-15
|
348 | 92.9 was 93.6 — |
| 8 | = |
morluto/rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Rank
2026-11-12: Rank rose 16 spots (#31 → #15)
|
A | 460.2k |
2026-11-15
|
4192 | 92.7 was 90.5 ▲2.8 |
| 9 | = | cline/cline Autonomous coding agent as an SDK, IDE extension, or CLI assistant. | A | 71.6k |
2026-11-13
|
148 | 92.5 was 92.3 ▼0.2 |
| 10 | = |
zereight/gitlab-mcp
MCP server for GitLab: 288 tools for projects, MRs, issues, pipelines, wikis and more via the GitLab REST/GraphQL API
Rank +1
2026-11-12: Rank rose 10 spots (#21 → #11)
|
A | 2.1k |
2026-11-15
|
551 | 92.3 was 90.4 ▲4.2 |
| =11 | ▲1 | livekit/agents A framework for building realtime voice AI agents 🤖🎙️📹 | A | 15.2k |
2026-11-15
|
260 | 92.1 was 90.6 ▼0.8 |
| =11 | ▲1 | microsoft/playwright-mcp Playwright MCP server | A | 39.7k |
2026-11-13
|
28 | 92.1 was 89.1 — |
| 13 | ▼2 | modelcontextprotocol/inspector Deterministic testing tools for MCP servers | A | 11.3k |
2026-11-12
|
380 | 92.0 was 88.6 ▼0.1 |
| 14 | = |
huggingface/lerobot
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Rank
2026-11-11: Rank rose 14 spots (#27 → #13)
|
A | 28.9k |
2026-11-15
|
128 | 91.8 was 91.8 ▲1.5 |
| =15 | = | DeusData/codebase-memory-mcp Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection. | A | 48.7k |
2026-11-14
|
1113 | 91.6 was 88.5 ▼1.3 |
| =15 | ▲1 | callstack/agent-device Open source device layer for AI coding agents: a CLI, MCP server, and typed Node.js API to control mobile, web, TV, and desktop apps on devices and simulators, locally or in the cloud. | A | 5.4k |
2026-11-15
|
565 | 91.6 was 88.5 ▼0.6 |
| 17 | ▼1 | mobile-next/mobile-mcp Mobile MCP: let AI agents drive your iOS and Android apps. MCP server for simulators, emulators and real devices. Works with Claude Code, Codex, Cursor and any MCP client. | A | 10.6k |
2026-11-11
|
29 | 91.5 was 88.3 ▼0.8 |
| =18 | = | hashgraph-online/hol-guard Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime. | A | 1.1k |
2026-11-15
|
2805 | 91.3 was 89.9 — |
| =18 | = | vercel-labs/agent-browser Browser automation CLI for AI agents | A | 51.3k |
2026-11-15
|
137 | 91.3 was 88.4 — |
| 20 | = | browserbase/stagehand The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more. | A | 26.1k |
2026-11-14
|
97 | 91.1 was 90.3 ▲0.1 |
| 21 | = | CursorTouch/Windows-MCP MCP Server for Computer Use in Windows | A | 11.7k |
2026-11-14
|
110 | 91.0 was 88.6 ▲0.4 |
| 22 | ▲2 | browser-use/browser-harness Let Claude Code, Codex or Cursor use your real Chrome, logged in as you. One prompt to set up. Open source, MIT. | A | 19.1k |
2026-11-15
|
89 | 90.8 was 87.3 ▲0.5 |
| 23 | = | supabase/mcp Connect Supabase to your AI assistants | A | 3.0k |
2026-11-14
|
60 | 90.7 was 87.2 — |
| 24 | ▼2 | openclaw/openclaw The AI that really does things. Any OS. Any Platform. The lobster way. 🦞 | A | 394.5k |
2026-11-15
|
17045 | 90.6 was 90.9 ▼0.7 |
| =25 | = | openai/openai-agents-python A lightweight, powerful framework for multi-agent workflows | A | 30.7k |
2026-11-15
|
75 | 90.5 was 93.6 ▼0.1 |
| =25 | = | strands-agents/harness-sdk Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud. | A | 9.2k |
2026-11-14
|
361 | 90.5 was 89.0 ▼0.1 |
| 27 | = | affaan-m/ECC The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. | A | 303.2k |
2026-11-09
|
374 | 90.3 was 88.7 ▼0.6 |
| =28 | ▲1 | n8n-io/n8n Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations. | A | 210.5k |
2026-11-15
|
1600 | 90.2 was 93.1 ▼0.2 |
| =28 | ▼1 | cloudflare/agents Build and deploy AI Agents on Cloudflare | A | 6.0k |
2026-11-14
|
114 | 90.2 was 87.6 — |
| 30 | ▲13 |
maximhq/bifrost
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of…
Rank +2
2026-11-15: Rank rose 13 spots (#43 → #30)
|
A | 9.6k |
2026-11-14
|
944 | 90.1 was 88.0 ▲0.3 |
| 31 | ▼1 | openai/codex Lightweight coding agent that runs in your terminal | A | 135.3k |
2026-11-15
|
1320 | 89.9 was 86.4 — |
| =32 | ▼1 | oaslananka/easyeda-mcp-pro MCP server for EasyEDA Pro, connecting AI agents to schematic and PCB workflows, controlled design operations, DRC, BOM sourcing, board analysis, and manufacturing export—with profile-gated tools and safety controls. | A | 70 |
2026-11-15
|
285 | 89.8 was 87.3 ▲1.0 |
| =32 | = |
pydantic/pydantic-ai
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
Rank
2026-11-11: Rank rose 21 spots (#54 → #33)
|
A | 21.2k |
2026-11-15
|
1414 | 89.8 was 91.7 ▲1.2 |
| =32 | = | apify/apify-mcp-server The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store. | A | 16.3k |
2026-11-13
|
205 | 89.8 was 86.8 — |
| =35 | ▼3 | openclaw/Peekaboo Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models. | A | 5.5k |
2026-11-14
|
77 | 89.7 was 86.2 ▼0.4 |
| =35 | ▼1 | mlflow/mlflow The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data. | A | 28.8k |
2026-11-15
|
607 | 89.7 was 90.3 ▲0.1 |
| =37 | = |
containers/kubernetes-mcp-server
Model Context Protocol (MCP) server for Kubernetes and OpenShift
Rank
2026-11-10: Rank rose 20 spots (#56 → #36)
|
A | 2.3k |
2026-11-14
|
118 | 89.6 was 85.2 ▲1.6 |
| =37 | ▼2 | software-mansion/argent An agentic toolkit to control, debug, and profile iOS and Android apps. Made by Software Mansion. | A | 3.2k |
2026-11-14
|
127 | 89.6 was 85.6 ▼0.2 |
| 39 | ▲1 | agentscope-ai/ReMe ReMe: Memory Management Kit for Agents - Remember Me, Refine Me. | A | 3.8k |
2026-11-14
|
76 | 89.5 was 87.6 ▲0.2 |
| 40 | ▼2 | thesysdev/openui The Open Standard for Generative UI | A | 15.2k |
2026-11-14
|
98 | 89.4 was 86.7 ▲0.3 |
| 41 | ▼2 | docling-project/docling Get your documents ready for gen AI | A | 70.6k |
2026-11-14
|
237 | 89.3 was 88.8 — |
| 42 | = |
headroomlabs-ai/headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Provider Added
2026-11-08: Runtime surface grew — new detected provider dependency: Google Gemini
|
A | 79.7k |
2026-11-15
|
429 | 89.2 was 91.1 — |
| 43 | ▼2 | Unstructured-IO/unstructured Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows… | A | 15.7k |
2026-11-14
|
82 | 89.1 was 90.5 — |
| =44 | ▲6 | NVIDIA/OpenShell OpenShell is the safe, private runtime for autonomous AI agents. | A | 21.6k |
2026-11-15
|
265 | 89.0 was 89.6 ▼0.1 |
| =44 | ▲1 | firecrawl/firecrawl Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥 | A | 201.8k |
2026-11-15
|
294 | 89.0 was 91.6 ▼0.1 |
| 46 | ▼2 |
composiohq/composio
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Rank +1
2026-11-13: Rank rose 21 spots (#66 → #45)
|
A | 31.1k |
2026-11-14
|
476 | 88.9 was 89.1 — |
| =47 | = |
firecrawl/firecrawl-mcp-server
Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.
Rank
2026-11-11: Rank dropped 14 spots (#35 → #49)
|
A | 7.8k |
2026-11-14
|
138 | 88.8 was 86.2 ▼0.9 |
| =47 | ▲23 |
QwenLM/qwen-code
An open-source AI coding agent that lives in your terminal.
Rank +3
2026-11-15: Rank rose 23 spots (#71 → #48)
|
A | 30.4k |
2026-11-15
|
1643 | 88.8 was 88.1 ▲3.0 |
| =49 | ▼1 | ihor-sokoliuk/mcp-searxng Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client | A | 1.4k |
2026-11-13
|
45 | 88.7 was 83.9 ▲0.1 |
| =49 | ▼1 | EverMind-AI/EverOS One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. | A | 13.9k |
2026-11-14
|
43 | 88.7 was 87.2 ▲0.2 |
| 51 | ▼6 | homeassistant-ai/ha-mcp Configure and automate Home Assistant with Claude, ChatGPT, and other AI assistants. | A | 7.8k |
2026-11-15
|
508 | 88.6 was 86.0 ▲0.3 |
| =52 | ▼1 |
a2aproject/A2A
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
Rank
2026-11-14: Rank dropped 13 spots (#38 → #51)
|
A | 26.5k |
2026-11-13
|
9 | 88.5 was 89.1 ▼0.3 |
| =52 | ▼1 | arc-mcp/arc-1 | A | 262 |
2026-11-14
|
150 | 88.5 was 84.0 ▲0.1 |
| =54 | = | cap-js/mcp-server MCP server for AI-assisted development of CAP applications | A | 118 |
2026-11-13
|
19 | 88.4 was 83.9 — |
| =54 | ▼2 | mongodb-js/mongodb-mcp-server A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters. | A | 1.2k |
2026-11-13
|
39 | 88.4 was 84.9 ▼0.2 |
| =56 | = | sipyourdrink-ltd/bernstein The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run | A | 1.2k |
2026-11-15
|
570 | 88.3 was 87.0 ▼0.4 |
| =56 | ▼2 | stickerdaniel/linkedin-mcp-server Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages. | A | 4.2k |
2026-11-14
|
102 | 88.3 was 83.7 ▲0.1 |
| =58 | ▼1 | oaslananka/kicad-mcp-pro MCP server for KiCad, connecting AI agents to schematic and PCB workflows, ERC/DRC validation, DFM checks, BOM analysis, and manufacturing preparation—with controlled edits and human-gated release workflows. | A | 216 |
2026-11-15
|
380 | 88.2 was 87.0 ▼0.3 |
| =58 | = | modelcontextprotocol/ext-apps Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers | A | 3.1k |
2026-11-10
|
14 | 88.2 was 83.6 ▲0.1 |
| =60 | ▲1 | volcengine/OpenViking Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | A | 42.2k |
2026-11-15
|
487 | 88.0 was 90.2 ▲0.4 |
| =60 | ▼3 | Softeria/ms-365-mcp-server A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Microsoft Office services through the Graph API | A | 1.1k |
2026-11-14
|
63 | 88.0 was 84.3 ▼0.4 |
| 62 | ▼2 | mcp-hangar/mcp-hangar MCP policy enforcement plane — deterministic policy on every Model Context Protocol call: identity, RFC 8707 audience binding, tool schema digest pinning, full audit trail. Python, self-hosted, MIT. | A | 17 |
2026-11-14
|
220 | 87.9 was 83.8 ▲0.1 |
| =63 | = | vishalsachdev/canvas-mcp Canvas LMS MCP server — up to 102 tools and 8 agent skills for students & educators. Works with Claude, Cursor, Codex, and 40+ agents. | A | 327 |
2026-11-15
|
273 | 87.8 was 84.0 ▲0.1 |
| =63 | ▼2 | punkpeye/fastmcp A TypeScript framework for building MCP servers. | A | 3.3k |
2026-11-11
|
78 | 87.8 was 83.0 ▼0.7 |
| =65 | ▼1 | sparfenyuk/mcp-proxy A bridge between Streamable HTTP and stdio MCP transports | A | 2.8k |
2026-11-09
|
33 | 87.7 was 83.9 ▼0.8 |
| =65 | ▼1 |
SylphxAI/anymd
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
Rank +1
2026-11-12: Rank rose 10 spots (#78 → #68)
|
A | 1.1k |
2026-11-15
|
60 | 87.7 was 82.8 ▼0.2 |
| 67 | ▼1 | zvec-ai/zvec-grep Local-first search across your workspace, built for humans and AI agents. | A | 4.3k |
2026-11-13
|
106 | 87.5 was 84.4 — |
| 68 | ▼1 |
browser-use/browser-use
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Provider Removed +5
2026-11-11: Runtime surface shrank — no longer detected: Amazon Bedrock, Groq
|
A | 121.0k |
2026-11-15
|
642 | 87.4 was 84.9 ▲14.5 |
| 69 | = | Skyvern-AI/skyvern Automate browser based workflows with AI | A | 23.4k |
2026-11-15
|
491 | 87.3 was 89.5 ▲0.1 |
| =70 | ▼2 | AIOSAI/AIPass Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero. | A | 317 |
2026-11-14
|
530 | 87.2 was 84.4 — |
| =70 | ▼1 |
botpress/botpress
The open-source hub to build & deploy GPT/LLM Agents ⚡️
Rank
2026-11-14: Rank rose 12 spots (#82 → #70)
|
A | 15.0k |
2026-11-13
|
34 | 87.2 was 85.6 ▲0.9 |
| =70 | = | hi-godot/godot-ai Production-grade MCP server and AI tools for the Godot engine. A Snap to install. Totally free and fun. | A | 3.5k |
2026-11-14
|
91 | 87.2 was 82.1 ▲0.4 |
| =73 | = |
pipecat-ai/pipecat
Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
Rank
2026-11-13: Rank dropped 12 spots (#63 → #75)
|
A | 17.3k |
2026-11-15
|
1589 | 87.1 was 88.4 ▼1.0 |
| =73 | = | triggerdotdev/trigger.dev Trigger.dev – build and deploy durable AI agents and workflows | A | 16.8k |
2026-11-13
|
387 | 87.1 was 85.0 — |
| =73 | = | langwatch/langwatch Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company. | A | 5.0k |
2026-11-15
|
519 | 87.1 was 84.2 ▲0.4 |
| 76 | = |
samuelgursky/davinci-resolve-mcp
MCP server integration for DaVinci Resolve Studio
Rank
2026-11-11: Rank dropped 11 spots (#65 → #76)
|
A | 4.1k |
2026-11-14
|
187 | 86.9 was 81.7 ▼0.6 |
| =77 | ▲1 |
ooples/token-optimizer-mcp
91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
Rank
2026-11-12: Rank rose 10 spots (#90 → #80)
|
A | 581 |
2026-11-15
|
61 | 86.8 was 82.3 ▲0.9 |
| =77 | ▲1 |
beenuar/AiSOC
Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
Rank
2026-11-11: Rank rose 17 spots (#98 → #81)
|
A | 7.7k |
2026-11-15
|
392 | 86.8 was 83.0 ▲1.5 |
| =77 | ▼2 | agno-agi/agno The self-managing agent platform | A | 43.2k |
2026-11-14
|
182 | 86.8 was 87.2 ▼0.2 |
| =80 | = | QwenAudio/qwen-audio-agent A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents | A | 3.2k |
2026-11-12
|
36 | 86.7 was 82.5 ▼0.3 |
| =80 | = | lancedb/lancedb Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less. | A | 11.9k |
2026-11-15
|
427 | 86.7 was 88.5 — |
| 82 | ▲1 | XBP-Europe/sagemath-mcp Stateful SageMath MCP server: 40 tools for symbolic math, algebra, number theory, graphs, plotting and claim verification. A persistent Sage session per client, an AST policy in front of it, and a hardened container as the real boundary. | A | 19 |
2026-11-14
|
53 | 86.5 was 81.8 ▲0.7 |
| 83 | ▼1 | vectorize-io/hindsight Hindsight: Agent Memory That Learns | A | 61.1k |
2026-11-14
|
483 | 86.4 was 86.3 ▼0.3 |
| 84 | = | getzep/graphiti Build Real-Time Knowledge Graphs for AI Agents | A | 32.8k |
2026-11-15
|
37 | 86.3 was 85.8 ▼0.3 |
| =85 | = |
dominik1001/caldav-mcp
🗓️ A CalDAV Model Context Protocol (MCP) server to expose calendar operations as tools for AI assistants.
Rank +1
2026-11-10: Rank rose 24 spots (#107 → #83)
|
A | 112 |
2026-11-13
|
131 | 86.1 was 80.2 ▲1.4 |
| =85 | = | browserstack/mcp-server BrowserStack's Official MCP Server | A | 153 |
2026-11-13
|
311 | 86.1 was 80.2 ▲1.0 |
| =85 | ▲1 |
stackql/stackql
Query, provision and operate Cloud, SaaS, API and Model Context Protocol (MCP) resources through a unified SQL-based framework for humans and AI agents.
Provider Added +1
2026-11-13: Runtime surface grew — new detected provider dependency: Amazon Bedrock
|
A | 1.1k |
2026-11-15
|
58 | 86.1 was 83.4 ▼1.1 |
| =88 | ▼1 |
topoteretes/cognee
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
Rank
2026-11-11: Rank dropped 10 spots (#85 → #95)
|
A | 33.3k |
2026-11-14
|
1005 | 85.9 was 88.2 ▲0.2 |
| =88 | ▲1 |
neomjs/neo
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.
Rank +4
2026-11-14: Rank dropped 31 spots (#59 → #90)
|
A | 3.3k |
2026-11-15
|
630 | 85.9 was 82.7 ▼2.4 |
| =88 | ▼1 | Prism-Shadow/penguin-harness 🐧 Unified and Stable RSI Platform | A | 3.2k |
2026-11-15
|
253 | 85.9 was 80.3 ▼0.4 |
| 91 | ▲1 | boxlite-ai/boxlite The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud. | A | 2.6k |
2026-11-15
|
218 | 85.7 was 84.5 — |
| =92 | ▼1 | lennix1337/Genexus18MCP GeneXus MCP server with native SDK support for GeneXus 16–18 plus basic legacy compatibility for GeneXus 8, 9, 10.1–10.3, and 15 via reflection/COM drivers. | A | 46 |
2026-11-14
|
593 | 85.6 was 79.6 ▼0.3 |
| =92 | = |
stripe/ai
One-stop shop for building AI-powered products and businesses with Stripe.
Provider Removed +1
2026-11-08: Runtime surface shrank — no longer detected: OpenAI
|
A | 2.1k |
2026-11-15
|
61 | 85.6 was 81.0 ▲0.1 |
| =94 | ▲8 | UI5/mcp-server The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework. | A | 108 |
2026-11-15
|
11 | 85.4 was 79.7 ▲0.5 |
| =94 | ▼1 | achiya-automation/safari-mcp Native Safari browser automation for AI agents. 98 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chrome DevTools MCP with 40-60% less CPU/heat on Apple Silicon. | A | 244 |
2026-11-13
|
29 | 85.4 was 79.4 ▼0.7 |
| 96 | ▼1 | chrisdoc/hevy-mcp Manage your Hevy workouts, routines, folders, and exercise templates. Create and update sessions faster, organize plans, and search exercises to build workouts quickly. Stay synced with changes so your training log is always up to date. | A | 541 |
2026-11-14
|
41 | 85.3 was 80.9 ▲0.2 |
| 97 | ▼1 |
cacheplane/threadplane
The open-source thread-plane for agents: chat, durable threads, persistence, human approvals, and generative UI for React and Angular, on LangGraph and AG-UI.
Rank
2026-11-08: Rank dropped 17 spots (#91 → #108)
|
A | 184 |
2026-11-15
|
310 | 85.2 was 83.9 ▲0.6 |
| =98 | = |
erayendes/app-store-connect-mcp
Heimdall: run App Store Connect, TestFlight and StoreKit 2 from your AI. 786 tools in 14 profiles, generated from Apple's OpenAPI spec. Worldwide pricing, offers, subscriptions, submissions and review triage in one call, with confirm-before-write safety and read-only mode. Runs locally via npx.
Rank +1
2026-11-12: Rank dropped 10 spots (#93 → #103)
|
A | 61 |
2026-11-13
|
24 | 85.1 was 79.4 ▼0.5 |
| =98 | = | SmartBear/smartbear-mcp SmartBear's official MCP Server | A | 44 |
2026-11-13
|
36 | 85.1 was 80.6 ▲0.3 |
| =98 | = | elgorro/aiquila Private AI for your Nextcloud — an MCP server (316 tools), a native Nextcloud app with chat and Coworkers, and one-command Hetzner deployment. | A | 40 |
2026-11-14
|
121 | 85.1 was 79.6 ▲0.4 |
Daily movers
Verify your agent or MCP server →
Paste a repo, package, or server URL — get a signed verdict.
Use HVTracker from your agent →
MCP server at
— trust checks answered for AI agents in the last 24h
see it live →
hvtracker.net/mcp — no auth, no install.
HKUDS/LightRAG
Simple, fast retrieval-augmented generation
★ 40.7k
HVTrust
ComposioHQ/composio
Tooling and context management for AI agents
★ 31.1k
HVTrust
deepset-ai/haystack
Open-source AI orchestration framework
★ 27.0k
HVTrust
AIOSAI/AIPass
Persistent workspace for AI agents
★ 317
HVTrust
sjkim1127/Reversecore_MCP
Security-first MCP server for reverse engineering
★ 222
HVTrust
cacheplane/threadplane
Open-source thread-plane for agents
★ 184
HVTrust
mcp-hangar/mcp-hangar
Policy enforcement plane for MCP calls
★ 17
HVTrust
Projects needing review
These listings stay active, but one or more automated eligibility checks need attention. The warning is surfaced here instead of being buried in raw metadata.
Better Godot MCP
repository is archived
Dynatrace MCP
repository is archived
Sfcc Dev MCP
repository is archived
Storybook MCP Addon
repository is archived
Claude Code
no declared license (GitHub license field is null)
DeepSeek-Reasonix
repository is archived