AI Trust Registry for open-source AI agent projects.
Independent trust scores for 1378 open-source AI agent projects and 385 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 | 26.7k |
2026-10-16
|
301 | 96.5 was 96.0 ▲0.2 |
| 2 | ▲3 | modelcontextprotocol/python-sdk The official Python SDK for Model Context Protocol servers and clients | A | 24.6k |
2026-10-16
|
40 | 95.0 was 93.7 ▲1.4 |
| =3 | = | langchain-ai/langgraph Build resilient agents. | A | 43.4k |
2026-10-16
|
103 | 94.5 was 93.9 ▲0.3 |
| =3 | ▼2 | modelcontextprotocol/typescript-sdk The official TypeScript SDK for Model Context Protocol servers and clients | A | 13.6k |
2026-10-14
|
52 | 94.5 was 92.2 ▼0.1 |
| 5 | ▼1 | openai/openai-agents-js A lightweight, powerful framework for multi-agent workflows and voice agents | A | 3.9k |
2026-10-16
|
101 | 94.1 was 93.9 — |
| 6 | = |
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
HVTrust
2026-10-10: HVTrust down 3.3pts (96.2 → 92.9)
|
A | 27.4k |
2026-10-16
|
615 | 93.8 was 91.2 ▼2.4 |
| 7 | = |
morluto/rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Rank +2
2026-10-13: Rank rose 21 spots (#31 → #10)
|
A | 286.2k |
2026-10-16
|
2697 | 93.4 was 91.8 ▲5.6 |
| 8 | = | livekit/agents A framework for building realtime voice AI agents 🤖🎙️📹 | A | 14.8k |
2026-10-16
|
199 | 92.6 was 91.3 ▲0.9 |
| 9 | = | mobile-next/mobile-mcp Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices) | A | 9.7k |
2026-10-15
|
47 | 92.3 was 89.4 ▼0.2 |
| =10 | ▲1 | modelcontextprotocol/inspector Visual testing tool for MCP servers | A | 11.1k |
2026-10-14
|
717 | 91.9 was 88.4 ▲0.5 |
| =10 | ▼1 | 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 | 26.1k |
2026-10-16
|
623 | 91.9 was 92.6 ▼0.7 |
| =10 | = |
callstack/agent-device
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
Provenance +3
2026-10-11: Package provenance attestation detected
|
A | 5.0k |
2026-10-16
|
696 | 91.9 was 88.8 ▲13.2 |
| 13 | = | cline/cline Autonomous coding agent as an SDK, IDE extension, or CLI assistant. | A | 70.4k |
2026-10-16
|
306 | 91.7 was 91.3 — |
| =14 | = | openai/openai-agents-python A lightweight, powerful framework for multi-agent workflows | A | 30.1k |
2026-10-15
|
231 | 91.5 was 94.9 — |
| =14 | = | DeusData/codebase-memory-mcp High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies. | A | 46.7k |
2026-10-16
|
1026 | 91.5 was 87.8 ▼0.7 |
| =14 | = | 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 | 207.7k |
2026-10-16
|
1465 | 91.5 was 93.1 — |
| 17 | = | microsoft/playwright-mcp Playwright MCP server | A | 38.2k |
2026-10-08
|
16 | 91.2 was 87.8 ▼0.4 |
| 18 | = | hashgraph-online/hol-guard Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime. | A | 914 |
2026-10-16
|
1819 | 91.0 was 89.4 ▼0.1 |
| 19 | = | 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 | 8.8k |
2026-10-16
|
304 | 90.7 was 89.3 ▲0.2 |
| =20 | ▲1 | huggingface/lerobot 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning | A | 28.2k |
2026-10-16
|
75 | 90.4 was 90.4 ▲0.5 |
| =20 | ▼1 |
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.
Rank
2026-10-10: Rank rose 24 spots (#46 → #22)
|
A | 281.1k |
2026-10-15
|
1029 | 90.4 was 88.9 ▲2.6 |
| 22 | = |
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.
Rank +2
2026-10-09: Rank rose 81 spots (#99 → #18)
|
A | 18.5k |
2026-10-15
|
102 | 90.3 was 86.5 ▼0.4 |
| 23 | ▲2 |
openclaw/openclaw
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Provider Added
2026-10-12: Runtime surface grew — new detected provider dependency: Postgres
|
A | 392.2k |
2026-10-16
|
17091 | 90.1 was 90.9 ▼1.0 |
| 24 | ▼1 | 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 | 5.3k |
2026-10-16
|
317 | 90.0 was 86.6 ▲0.1 |
| 25 | ▼1 | openai/codex Lightweight coding agent that runs in your terminal | A | 129.5k |
2026-10-16
|
1470 | 89.9 was 86.4 ▼0.1 |
| 26 | = | a2aproject/A2A Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications. | A | 26.2k |
2026-10-16
|
25 | 89.8 was 90.4 ▼0.1 |
| 27 | = | cloudflare/agents Build and deploy AI Agents on Cloudflare | A | 5.8k |
2026-10-16
|
183 | 89.7 was 86.8 — |
| =28 | ▲9 | 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… | A | 8.9k |
2026-10-16
|
1142 | 89.6 was 87.4 ▲0.1 |
| =28 | ▼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 | 28.4k |
2026-10-16
|
469 | 89.6 was 90.2 — |
| =28 | ▼1 | docling-project/docling Get your documents ready for gen AI | A | 69.0k |
2026-10-16
|
260 | 89.6 was 89.1 ▼0.1 |
| 31 | ▼1 |
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.
Provenance +4
2026-10-15: Package provenance attestation detected
|
A | 75.5k |
2026-10-16
|
514 | 89.4 was 91.3 ▲12.8 |
| 32 | ▼1 |
QwenLM/qwen-code
An open-source AI coding agent that lives in your terminal.
Rank +1
2026-10-13: Rank rose 12 spots (#44 → #32)
|
A | 28.5k |
2026-10-16
|
1098 | 89.3 was 87.4 ▼0.1 |
| =33 | = |
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.
Provider Added
2026-10-13: Runtime surface grew — new detected provider dependency: Anthropic
|
A | 3.9k |
2026-10-16
|
274 | 89.2 was 85.0 ▲0.1 |
| =33 | = | 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 | 11.5k |
2026-10-16
|
149 | 89.2 was 86.0 ▼0.2 |
| =33 | ▼3 | 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 | 25.7k |
2026-10-16
|
96 | 89.2 was 88.7 ▲0.3 |
| =36 | = | 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 | 1.3k |
2026-10-16
|
414 | 89.1 was 88.1 ▲0.4 |
| =36 | ▲1 | software-mansion/argent An agentic toolkit to control, debug, and profile iOS and Android apps. Made by Software Mansion. | A | 3.0k |
2026-10-16
|
103 | 89.1 was 84.9 — |
| 38 | ▼3 | ihor-sokoliuk/mcp-searxng Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client | A | 1.3k |
2026-10-13
|
57 | 89.0 was 84.3 — |
| 39 | = |
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.
Rank
2026-10-09: Rank rose 19 spots (#57 → #38)
|
A | 132 |
2026-10-16
|
458 | 88.9 was 86.9 ▲0.6 |
| 40 | = |
thesysdev/openui
The Open Standard for Generative UI
Rank
2026-10-15: Rank rose 11 spots (#51 → #40)
|
A | 11.3k |
2026-10-16
|
135 | 88.8 was 86.0 ▲1.1 |
| 41 | = | supabase/mcp Connect Supabase to your AI assistants | A | 3.0k |
2026-10-16
|
20 | 88.6 was 84.2 ▲0.3 |
| 42 | ▲1 | cap-js/mcp-server MCP server for AI-assisted development of CAP applications | A | 115 |
2026-10-16
|
30 | 88.5 was 84.0 ▲0.5 |
| =43 | ▼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 +2
2026-10-14: Rank rose 17 spots (#58 → #41)
|
A | 1.0k |
2026-10-16
|
205 | 88.4 was 83.9 ▲1.5 |
| =43 | = |
hi-godot/godot-ai
Production-grade MCP server and AI tools for the Godot engine. A Snap to install. Totally free and fun.
Scorecard +4
2026-10-13: OSSF Scorecard: 6.0/10
|
A | 3.0k |
2026-10-16
|
64 | 88.4 was 83.8 ▲11.2 |
| =43 | = | pydantic/pydantic-ai How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. | A | 20.7k |
2026-10-16
|
1007 | 88.4 was 90.0 ▲0.1 |
| =43 | = | firecrawl/firecrawl Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥 | A | 192.1k |
2026-10-16
|
260 | 88.4 was 90.9 — |
| 47 | = | CursorTouch/Windows-MCP MCP Server for Computer Use in Windows | A | 9.2k |
2026-10-16
|
40 | 88.3 was 84.7 ▲0.9 |
| =48 | ▲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.
Mcp Status Changed +1
2026-10-12: Detected MCP server support changed: declared → implemented
|
A | 13.4k |
2026-10-16
|
32 | 88.1 was 86.3 ▲3.0 |
| =48 | ▼1 | arc-mcp/arc-1 | A | 223 |
2026-10-14
|
152 | 88.1 was 83.5 ▲0.7 |
| =50 | = |
volcengine/OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Provider Added
2026-10-15: Runtime surface grew — new detected provider dependency: Redis
|
A | 40.1k |
2026-10-16
|
447 | 88.0 was 90.2 ▼0.2 |
| =50 | = | homeassistant-ai/ha-mcp The Unofficial and Awesome Home Assistant MCP Server | A | 5.1k |
2026-10-16
|
382 | 88.0 was 85.1 ▲0.2 |
| =50 | = | mongodb-js/mongodb-mcp-server A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters. | A | 1.1k |
2026-10-16
|
62 | 88.0 was 84.3 ▼0.1 |
| =53 | = | 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 | 15.6k |
2026-10-15
|
31 | 87.8 was 88.9 ▲0.5 |
| =53 | ▲1 |
agentscope-ai/ReMe
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
Rank
2026-10-12: Rank dropped 12 spots (#37 → #49)
|
A | 3.6k |
2026-10-16
|
51 | 87.8 was 85.2 ▼1.0 |
| =53 | ▼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
2026-10-10: Rank dropped 17 spots (#28 → #45)
|
A | 3.3k |
2026-10-16
|
472 | 87.8 was 83.0 ▼1.7 |
| 56 | ▲4 | getzep/graphiti Build Real-Time Knowledge Graphs for AI Agents | A | 31.8k |
2026-10-15
|
45 | 87.7 was 87.9 ▲0.5 |
| 57 | ▲7 | oaslananka/easyeda-mcp-pro Production-grade 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 | 57 |
2026-10-16
|
57 | 87.6 was 84.2 ▲0.9 |
| 58 | ▲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 | 217 |
2026-10-14
|
152 | 87.5 was 82.1 ▼0.2 |
| =59 | ▼1 | sjkim1127/Reversecore_MCP A security-first MCP server that empowers AI agents to perform automated reverse engineering, malware analysis, forensics, vulnerability research, and SAST — powered by Radare2, YARA, LIEF, Capstone, and more. | A | 211 |
2026-10-16
|
169 | 87.4 was 84.3 ▲0.1 |
| =59 | ▲1 | zereight/gitlab-mcp First gitlab mcp for you, building together | A | 2.0k |
2026-10-16
|
368 | 87.4 was 83.5 ▲0.1 |
| =59 | ▼4 | punkpeye/fastmcp A TypeScript framework for building MCP servers. | A | 3.3k |
2026-10-14
|
60 | 87.4 was 82.4 ▲0.3 |
| =62 | = |
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.
Rank +3
2026-10-14: Rank rose 11 spots (#73 → #62)
|
A | 18 |
2026-10-16
|
112 | 87.3 was 83.0 ▼0.3 |
| =62 | = | agno-agi/agno Build, run, and manage agent platforms. | A | 42.8k |
2026-10-16
|
136 | 87.3 was 87.8 ▼0.1 |
| 64 | ▼8 | vercel-labs/agent-browser Browser automation CLI for AI agents | A | 44.1k |
2026-10-16
|
25 | 87.2 was 85.5 ▼0.5 |
| =65 | = | 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 | 18 |
2026-10-16
|
198 | 87.1 was 82.7 ▲0.4 |
| =65 | ▲5 | QwenAudio/qwen-audio-agent A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents | A | 2.9k |
2026-10-16
|
92 | 87.1 was 83.0 ▲0.9 |
| =67 | ▼1 | triggerdotdev/trigger.dev Trigger.dev – build and deploy durable AI agents and workflows | A | 16.6k |
2026-10-16
|
243 | 87.0 was 84.8 ▲0.2 |
| =67 | ▲6 |
langwatch/langwatch
Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
Provider Removed +2
2026-10-13: Runtime surface shrank — no longer detected: Amazon Bedrock, ElevenLabs, OpenAI, Postgres, Redis
|
A | 5.0k |
2026-10-16
|
264 | 87.0 was 84.1 ▲3.9 |
| 69 | ▼1 | botpress/botpress The open-source hub to build & deploy GPT/LLM Agents ⚡️ | A | 15.0k |
2026-10-13
|
27 | 86.9 was 85.2 ▲0.1 |
| =70 | ▲6 | UI5/mcp-server The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework. | A | 103 |
2026-10-14
|
28 | 86.8 was 81.6 ▲0.4 |
| =70 | ▼1 | 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 |
2026-10-15
|
40 | 86.8 was 82.6 ▲0.5 |
| =72 | ▼5 | 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 | 295 |
2026-10-15
|
282 | 86.7 was 82.5 ▲0.7 |
| =72 | ▼4 |
lancedb/lancedb
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
Rank
2026-10-11: Rank dropped 25 spots (#43 → #68)
|
A | 11.7k |
2026-10-16
|
168 | 86.7 was 88.5 ▼1.1 |
| 74 | ▼2 | 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 | 514 |
2026-10-16
|
79 | 86.6 was 82.7 ▼0.3 |
| =75 | = | traceloop/openllmetry Open-source observability for your GenAI or LLM application, based on OpenTelemetry | A | 7.5k |
2026-10-13
|
18 | 86.5 was 85.4 ▲0.4 |
| =75 | ▼3 | modelcontextprotocol/ext-apps Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers | A | 3.0k |
2026-09-25
|
8 | 86.5 was 81.2 ▼0.8 |
| =75 | ▲8 |
containers/kubernetes-mcp-server
Model Context Protocol (MCP) server for Kubernetes and OpenShift
Rank +1
2026-10-14: Rank rose 13 spots (#92 → #79)
|
A | 2.2k |
2026-10-16
|
54 | 86.5 was 80.7 ▲1.4 |
| 78 | ▲1 | mem0ai/mem0 The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production. | A | 67.3k |
2026-10-16
|
44 | 86.3 was 88.6 ▲0.2 |
| 79 | ▼2 |
Skyvern-AI/skyvern
Automate browser based workflows with AI
Rank
2026-10-12: Rank dropped 14 spots (#59 → #73)
|
A | 23.2k |
2026-10-16
|
265 | 86.2 was 88.3 ▼0.8 |
| =80 | = | AIOSAI/AIPass Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero. | A | 287 |
2026-10-16
|
664 | 86.1 was 84.0 ▲1.3 |
| =80 | ▲1 | ooples/token-optimizer-mcp Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients. | A | 549 |
2026-10-16
|
77 | 86.1 was 82.7 ▲1.0 |
| =82 | ▲1 | browserstack/mcp-server BrowserStack's Official MCP Server | A | 155 |
2026-10-16
|
202 | 85.9 was 79.9 ▲0.3 |
| =82 | ▲1 |
sparfenyuk/mcp-proxy
A bridge between Streamable HTTP and stdio MCP transports
Rank +4
2026-10-12: Rank rose 11 spots (#97 → #86)
|
A | 2.8k |
2026-10-14
|
20 | 85.9 was 81.3 ▲11.5 |
| 84 | ▲4 | pipecat-ai/pipecat Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community. | A | 16.5k |
2026-10-16
|
967 | 85.8 was 86.8 ▲0.8 |
| 85 | ▲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
2026-10-09: Rank rose 11 spots (#90 → #79)
|
A | 32.4k |
2026-10-16
|
789 | 85.6 was 87.7 ▼0.2 |
| =86 | ▼5 | samuelgursky/davinci-resolve-mcp MCP server integration for DaVinci Resolve Studio | A | 3.6k |
2026-10-15
|
164 | 85.5 was 79.8 ▼0.8 |
| =86 | ▲3 |
boxlite-ai/boxlite
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.
Provider Added
2026-10-13: Runtime surface grew — new detected provider dependency: Anthropic
|
A | 2.5k |
2026-10-16
|
141 | 85.5 was 84.2 ▲0.1 |
| =88 | ▲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 +2
2026-10-13: Rank dropped 39 spots (#58 → #97)
|
A | 2.4k |
2026-10-14
|
899 | 85.3 was 80.8 ▲0.4 |
| =88 | ▲2 |
firecrawl/firecrawl-mcp-server
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Tool Surface Changed +2
2026-10-10: Detected tool/plugin surface changed: declared → none
|
A | 7.6k |
2026-10-16
|
255 | 85.3 was 81.2 ▼0.2 |
| 90 | ▼3 |
cacheplane/threadplane
The open-source thread-plane for agents: chat, durable threads, persistence, human approvals, and generative UI for Angular, on LangGraph and AG-UI.
Rank +5
2026-10-15: Rank rose 16 spots (#103 → #87)
|
A | 305 |
2026-10-16
|
351 | 85.2 was 83.9 ▲1.3 |
| =91 | ▲5 | swimmwatch/cloakbrowser-mcp ⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport. | A | 167 |
2026-10-16
|
32 | 85.1 was 79.4 ▼0.9 |
| =91 | ▲5 |
nousresearch/hermes-agent
The agent that grows with you
Provider Added +10
2026-10-14: Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
|
A | 254.3k |
2026-10-16
|
17649 | 85.1 was 87.8 ▼0.8 |
| =91 | ▲1 |
vectorize-io/hindsight
Hindsight: Agent Memory That Learns
Rank
2026-10-13: Rank dropped 14 spots (#81 → #95)
|
A | 50.4k |
2026-10-16
|
644 | 85.1 was 85.4 ▼0.8 |
| =94 | ▼2 | pvliesdonk/markdown-vault-mcp Generic markdown vault MCP with hybrid search | A | 34 |
2026-10-15
|
149 | 84.9 was 79.7 ▲0.1 |
| =94 | ▲3 | Canner/WrenAI GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more. | A | 17.9k |
2026-10-16
|
32 | 84.9 was 80.7 ▼0.8 |
| =96 | ▲6 |
erayendes/app-store-connect-mcp
Heimdall — MCP server for the Apple App Store Connect API and App Store Server API (StoreKit 2). 902 tools across 13 profiles, generated from Apple's OpenAPI spec, plus one-call macros for worldwide pricing, submission readiness and metadata diffs, and confirm-before-write safety. Works with…
Rank
2026-10-10: Rank rose 10 spots (#120 → #110)
|
A | 53 |
2026-10-16
|
52 | 84.7 was 79.0 ▲2.5 |
| =96 | ▼4 |
vespa-engine/vespa
The AI search platform
Rank +1
2026-10-15: Rank dropped 15 spots (#78 → #93)
|
A | 7.1k |
2026-10-16
|
771 | 84.7 was 85.0 ▼0.6 |
| 98 | ▲1 | stripe/ai One-stop shop for building AI-powered products and businesses with Stripe. | A | 2.0k |
2026-10-16
|
35 | 84.6 was 79.9 ▼0.2 |
| =99 | ▲4 | anyproto/anytype-mcp An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language. | A | 533 |
2026-10-13
|
20 | 84.4 was 79.4 ▲0.2 |
| =99 | = |
HKUDS/LightRAG
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
Rank
2026-10-10: Rank dropped 10 spots (#86 → #96)
|
A | 40.2k |
2026-10-15
|
123 | 84.4 was 85.3 ▼0.8 |
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.
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
Storybook MCP Addon
repository is archived
Solace Agent Mesh
repository is archived
Claude Code
no declared license (GitHub license field is null)
Flowise
repository is archived