AI Trust Registry for open-source AI agent projects.
Independent trust scores for 1346 open-source AI agent projects and 359 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 | 26.6k |
2026-10-02
|
255 | 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 | 27.1k |
2026-10-03
|
505 | 96.2 was 94.5 — |
| =3 | ▲1 | openai/openai-agents-js A lightweight, powerful framework for multi-agent workflows and voice agents | A | 3.9k |
2026-10-02
|
157 | 93.9 was 93.6 ▲0.2 |
| =3 | ▼1 | DeusData/codebase-memory-mcp High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies. | A | 45.7k |
2026-10-03
|
546 | 93.9 was 91.3 ▲1.5 |
| 5 | ▲1 | langchain-ai/langgraph Build resilient agents. | A | 42.7k |
2026-10-03
|
56 | 93.1 was 92.3 ▲0.4 |
| 6 | ▼1 |
mobile-next/mobile-mcp
Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)
Tool Surface Changed +1
2026-10-03: Detected tool/plugin surface changed: none → declared
|
A | 8.6k |
2026-10-02
|
81 | 93.0 was 90.4 ▲0.1 |
| 7 | ▲2 | 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 | 25.7k |
2026-10-03
|
532 | 92.2 was 93.0 ▲0.4 |
| 8 | ▼1 | cline/cline Autonomous coding agent as an SDK, IDE extension, or CLI assistant. | A | 69.8k |
2026-10-03
|
316 | 92.1 was 91.8 ▲0.4 |
| =9 | ▼1 | 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 | 738 |
2026-10-03
|
796 | 91.7 was 90.5 ▼0.2 |
| =9 | ▲1 | livekit/agents A framework for building realtime voice AI agents 🤖🎙️📹 | A | 14.5k |
2026-10-03
|
175 | 91.7 was 90.0 ▲0.1 |
| 11 | ▼1 | openai/openai-agents-python A lightweight, powerful framework for multi-agent workflows | A | 29.8k |
2026-10-02
|
255 | 91.5 was 94.9 ▲0.2 |
| =12 | ▲2 | modelcontextprotocol/inspector Visual testing tool for MCP servers | A | 11.0k |
2026-10-02
|
693 | 91.3 was 87.5 ▲1.5 |
| =12 | ▼1 | microsoft/playwright-mcp Playwright MCP server | A | 37.8k |
2026-09-28
|
16 | 91.3 was 88.0 ▼0.3 |
| 14 | ▼1 |
openclaw/openclaw
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
License
2026-10-03: License changed from NOASSERTION to MIT
|
A | 391.2k |
2026-10-03
|
17324 | 91.2 was 91.3 ▲0.1 |
| 15 | = | maximhq/bifrost Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS. | A | 8.5k |
2026-10-03
|
819 | 91.0 was 89.1 ▲0.7 |
| 16 | = | 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 | 8.6k |
2026-10-02
|
248 | 90.4 was 88.9 ▼0.1 |
| 17 | = |
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 +1
2026-09-27: Rank rose 23 spots (#43 → #20)
|
A | 3.3k |
2026-10-03
|
542 | 90.2 was 86.4 ▲2.4 |
| 18 | = | 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 | 206.6k |
2026-10-03
|
1403 | 90.1 was 91.2 ▼1.4 |
| 19 | = | openai/codex Lightweight coding agent that runs in your terminal | A | 127.7k |
2026-10-03
|
1596 | 90.0 was 86.6 ▲0.1 |
| =20 | = | huggingface/lerobot 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning | A | 27.9k |
2026-10-03
|
69 | 89.9 was 89.9 ▼0.1 |
| =20 | ▲1 | cloudflare/agents Build and deploy AI Agents on Cloudflare | A | 5.8k |
2026-10-02
|
146 | 89.9 was 87.1 ▲0.2 |
| =22 | ▲8 | 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 | 28.2k |
2026-10-03
|
447 | 89.6 was 90.2 ▲1.0 |
| =22 | ▲1 | docling-project/docling Get your documents ready for gen AI | A | 68.3k |
2026-10-03
|
163 | 89.6 was 89.1 ▲0.4 |
| =24 | ▲1 | sipyourdrink-ltd/bernstein The open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run | A | 1.4k |
2026-10-03
|
570 | 89.3 was 88.4 — |
| =24 | ▲3 |
pydantic/pydantic-ai
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
Tool Surface Changed +2
2026-09-30: Detected tool/plugin surface changed: none → declared
|
A | 20.4k |
2026-10-03
|
761 | 89.3 was 91.1 ▼0.1 |
| =24 | ▼5 | modelcontextprotocol/ext-apps Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers | A | 2.9k |
2026-09-25
|
37 | 89.3 was 85.2 ▲0.2 |
| =24 | = | software-mansion/argent An agentic toolkit to control, debug, and profile iOS and Android apps. Made by Software Mansion. | A | 3.0k |
2026-10-03
|
105 | 89.3 was 85.1 ▼0.1 |
| 28 | ▼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 | 3.7k |
2026-10-03
|
219 | 89.2 was 85.0 ▲0.1 |
| =29 | ▲2 |
a2aproject/A2A
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
Rank +1
2026-10-02: Rank rose 26 spots (#57 → #31)
|
A | 26.0k |
2026-10-02
|
14 | 89.1 was 89.7 ▲0.1 |
| =29 | ▼7 | browser-use/browser-harness Browser Harness | Self-healing harness that enables LLMs to complete any task. | A | 18.3k |
2026-09-27
|
30 | 89.1 was 84.9 ▼0.7 |
| 31 | ▼2 | 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 | 9.5k |
2026-10-02
|
73 | 88.9 was 85.6 ▲0.3 |
| 32 | ▲4 | agentscope-ai/ReMe ReMe: Memory Management Kit for Agents - Remember Me, Refine Me. | A | 3.5k |
2026-10-03
|
52 | 88.8 was 86.5 — |
| 33 | ▼1 | ihor-sokoliuk/mcp-searxng Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client | A | 1.3k |
2026-09-29
|
71 | 88.7 was 83.8 — |
| =34 | = | mongodb-js/mongodb-mcp-server A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters. | A | 1.1k |
2026-10-02
|
79 | 88.6 was 85.1 ▲0.2 |
| =34 | = | 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 | 25.5k |
2026-10-02
|
69 | 88.6 was 87.9 ▲0.1 |
| 36 | ▼3 | supabase/mcp Connect Supabase to your AI assistants | A | 2.9k |
2026-10-03
|
18 | 88.5 was 84.0 ▼0.4 |
| =37 | ▲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 | 273 |
2026-10-03
|
170 | 88.1 was 84.4 ▲0.7 |
| =37 | ▲1 | 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 | 15.5k |
2026-10-03
|
18 | 88.1 was 87.7 ▲0.4 |
| =39 | ▲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
2026-09-30: Rank dropped 20 spots (#23 → #43)
|
A | 272.1k |
2026-10-02
|
395 | 88.0 was 85.4 ▼1.7 |
| =39 | ▲1 | firecrawl/firecrawl 🔥 Supercharge your AI agents with data from the web and beyond. A web data API to search, scrape, and access more sources. | A | 188.2k |
2026-10-03
|
219 | 88.0 was 90.4 — |
| =41 | ▲2 | volcengine/OpenViking Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | A | 39.2k |
2026-10-03
|
442 | 87.9 was 89.8 ▼0.2 |
| =41 | ▼4 |
QwenLM/qwen-code
An open-source AI coding agent that lives in your terminal.
Rank
2026-09-27: Rank dropped 13 spots (#24 → #37)
|
A | 28.3k |
2026-10-03
|
1121 | 87.9 was 85.5 ▼1.5 |
| 43 | ▲2 | vercel-labs/agent-browser Browser automation CLI for AI agents | A | 43.5k |
2026-10-03
|
36 | 87.8 was 86.3 ▲0.1 |
| =44 | ▼7 | 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 | 496 |
2026-10-03
|
83 | 87.7 was 84.3 ▼0.1 |
| =44 | ▲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.
Rank
2026-09-30: Rank rose 10 spots (#54 → #44)
|
A | 209 |
2026-10-03
|
150 | 87.7 was 82.4 ▲0.7 |
| =44 | ▼2 | homeassistant-ai/ha-mcp The Unofficial and Awesome Home Assistant MCP Server | A | 4.9k |
2026-10-03
|
342 | 87.7 was 84.7 ▲0.3 |
| =44 | = | thesysdev/openui The Open Standard for Generative UI | A | 10.0k |
2026-10-03
|
100 | 87.7 was 85.9 ▲0.1 |
| =48 | ▲2 | agno-agi/agno Build, run, and manage agent platforms. | A | 42.5k |
2026-10-03
|
120 | 87.4 was 88.0 ▲0.1 |
| =48 | ▲2 | punkpeye/fastmcp A TypeScript framework for building MCP servers. | A | 3.3k |
2026-09-30
|
60 | 87.4 was 82.4 ▼0.1 |
| 50 | ▼2 | cap-js/mcp-server MCP server for AI-assisted development of CAP applications | A | 112 |
2026-10-02
|
20 | 87.3 was 82.3 ▲0.3 |
| 51 | ▲1 |
arc-mcp/arc-1
Rank
2026-09-30: Rank dropped 15 spots (#38 → #53)
|
A | 209 |
2026-10-03
|
116 | 87.2 was 82.1 ▼0.9 |
| =52 | ▲2 | zereight/gitlab-mcp First gitlab mcp for you, building together | A | 2.0k |
2026-10-03
|
229 | 87.1 was 83.0 ▼0.1 |
| =52 | ▲49 |
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 +8
2026-10-03: Rank rose 49 spots (#102 → #53)
|
A | 1.0k |
2026-10-03
|
159 | 87.1 was 82.0 ▲4.1 |
| =54 | ▲3 | Skyvern-AI/skyvern Automate browser based workflows with AI | A | 23.1k |
2026-10-03
|
261 | 87.0 was 89.2 ▲0.1 |
| =54 | ▼6 |
triggerdotdev/trigger.dev
Trigger.dev – build and deploy durable AI agents and workflows
Provider Added
2026-10-03: Runtime surface grew — new detected provider dependency: Anthropic
|
A | 16.5k |
2026-10-02
|
240 | 87.0 was 84.8 ▼0.8 |
| 56 | = | 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 | 16 |
2026-09-29
|
121 | 86.8 was 81.1 — |
| 57 | ▼4 | botpress/botpress The open-source hub to build & deploy GPT/LLM Agents ⚡️ | A | 14.9k |
2026-10-02
|
29 | 86.6 was 84.9 — |
| =58 | ▼3 | 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 | 16 |
2026-10-01
|
234 | 86.4 was 81.7 ▼1.0 |
| =58 | = |
samuelgursky/davinci-resolve-mcp
MCP server integration for DaVinci Resolve Studio
Rank
2026-09-30: Rank rose 26 spots (#84 → #58)
|
A | 3.3k |
2026-10-03
|
281 | 86.4 was 81.0 ▲0.6 |
| =58 | ▼2 | 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 | 1.0k |
2026-10-02
|
26 | 86.4 was 82.0 ▼0.2 |
| 61 | ▼1 | UI5/mcp-server The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework. | A | 101 |
2026-09-30
|
24 | 86.3 was 80.9 ▲0.1 |
| 62 | ▼1 | getzep/graphiti Build Real-Time Knowledge Graphs for AI Agents | A | 31.4k |
2026-10-02
|
34 | 86.2 was 85.7 ▼0.8 |
| =63 | ▲2 | browserstack/mcp-server BrowserStack's Official MCP Server | A | 151 |
2026-10-01
|
142 | 86.0 was 80.0 ▲0.8 |
| =63 | ▲7 |
CursorTouch/Windows-MCP
MCP Server for Computer Use in Windows
Rank
2026-09-30: Rank dropped 11 spots (#65 → #76)
|
A | 7.7k |
2026-10-03
|
24 | 86.0 was 81.4 ▲0.2 |
| =63 | ▼2 | mem0ai/mem0 The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production. | A | 66.5k |
2026-10-01
|
46 | 86.0 was 88.3 ▼0.1 |
| =66 | = |
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
2026-10-01: Rank dropped 14 spots (#56 → #70)
|
A | 116 |
2026-10-03
|
190 | 85.9 was 82.6 ▼0.6 |
| =66 | ▼5 | 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 | A | 31.3k |
2026-10-03
|
769 | 85.9 was 88.2 ▼0.2 |
| =66 | ▼1 | QwenAudio/qwen-audio-agent A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents | A | 2.8k |
2026-09-28
|
214 | 85.9 was 81.3 — |
| =66 | ▼1 |
vectorize-io/hindsight
Hindsight: Agent Memory That Learns
Rank
2026-09-26: Rank rose 11 spots (#82 → #71)
|
A | 45.0k |
2026-10-02
|
558 | 85.9 was 86.3 ▲0.1 |
| =66 | ▼1 |
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 +7
2026-09-30: Detected tool/plugin surface changed: none → declared
|
A | 7.5k |
2026-10-03
|
154 | 85.9 was 83.2 ▲13.2 |
| 71 | ▼1 |
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.
Rank
2026-10-01: Rank dropped 12 spots (#61 → #73)
|
A | 50 |
2026-10-01
|
33 | 85.8 was 81.5 ▲0.5 |
| 72 | ▲13 |
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 +1
2026-10-03: Rank rose 13 spots (#85 → #72)
|
A | 65 |
2026-10-03
|
329 | 85.7 was 84.4 ▲2.0 |
| =73 | ▼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 | 13.3k |
2026-10-01
|
26 | 85.6 was 84.9 ▼0.7 |
| =73 | ▲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 | 2.4k |
2026-10-03
|
118 | 85.6 was 83.8 ▼0.2 |
| =73 | ▼1 | StuMason/coolify-mcp MCP server for Coolify — 42 optimized tools for managing self-hosted PaaS through AI assistants | A | 608 |
2026-10-02
|
109 | 85.6 was 80.9 ▲0.1 |
| =73 | = |
can1357/oh-my-pi
⌥ Coding agent with the IDE wired in. Built by Stencil Labs.
Rank +3
2026-10-02: Rank rose 31 spots (#107 → #76)
|
A | 34.2k |
2026-10-03
|
5849 | 85.6 was 86.1 ▲0.9 |
| =77 | = | cameronrye/openzim-mcp OpenZIM MCP is a modern, secure, and high-performance MCP (Model Context Protocol) server that enables AI models to access and search ZIM format knowledge bases offline. | A | 144 |
2026-10-01
|
22 | 85.4 was 80.6 ▼0.2 |
| =77 | = | pipecat-ai/pipecat Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community. | A | 16.2k |
2026-10-03
|
1073 | 85.4 was 86.3 ▲0.7 |
| =77 | ▲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.
Rank
2026-10-02: Rank dropped 10 spots (#72 → #82)
|
A | 17.8k |
2026-10-02
|
37 | 85.4 was 81.4 ▼0.1 |
| =77 | ▼1 | containers/kubernetes-mcp-server Model Context Protocol (MCP) server for Kubernetes and OpenShift | A | 2.1k |
2026-10-02
|
33 | 85.4 was 79.4 ▲0.5 |
| 81 | ▼1 | HKUDS/LightRAG [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation | A | 40.0k |
2026-10-03
|
653 | 85.3 was 86.4 ▲0.1 |
| =82 | ▲63 |
open-webui/open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Rank +7
2026-10-03: Rank rose 63 spots (#145 → #82)
|
A | 153.9k |
2026-10-03
|
317 | 85.2 was 89.8 ▼0.1 |
| =82 | ▼2 |
Hmbown/CodeWhale
Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
Rank
2026-10-02: Rank dropped 22 spots (#59 → #81)
|
A | 41.0k |
2026-10-03
|
3305 | 85.2 was 81.9 ▼1.9 |
| 84 | ▼1 | AIOSAI/AIPass Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero. | A | 287 |
2026-10-03
|
268 | 85.1 was 82.7 ▼0.6 |
| 85 | ▼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.
Rank
2026-10-01: Rank dropped 11 spots (#75 → #86)
|
A | 538 |
2026-10-03
|
58 | 85.0 was 81.1 ▼0.9 |
| 86 | ▲2 |
wandb/weave
Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.
Rank
2026-09-28: Rank dropped 13 spots (#73 → #86)
|
A | 1.1k |
2026-10-03
|
71 | 84.9 was 85.2 ▼1.0 |
| =87 | ▲2 | stripe/ai One-stop shop for building AI-powered products and businesses with Stripe. | A | 1.9k |
2026-10-03
|
27 | 84.8 was 80.2 — |
| =87 | ▼15 |
vespa-engine/vespa
The AI search platform
Rank +1
2026-10-03: Rank dropped 15 spots (#73 → #88)
|
A | 7.1k |
2026-10-03
|
595 | 84.8 was 85.1 ▲0.5 |
| 89 | ▼3 |
dynatrace-oss/dynatrace-managed-mcp
An MCP server for self-hosted Dynatrace Managed platform
Rank
2026-09-28: Rank rose 23 spots (#103 → #80)
|
A | 32 |
2026-10-01
|
59 | 84.7 was 80.0 ▲1.0 |
| =90 | ▲4 |
getnable/finopsmcp
The headless FinOps intelligence layer: API-first, agent-first cost control for cloud + AI. Connect your cloud stack in Claude, Cursor, or the terminal, and gate what agents do to your infra before they act. Propose-only. Open source, local-first.
Rank
2026-09-27: Rank rose 21 spots (#107 → #86)
|
A | 18 |
2026-10-03
|
301 | 84.6 was 81.3 ▲1.2 |
| =90 | ▼1 |
mnemoverse/mcp-memory-server
Hosted persistent memory for AI agents over MCP. Tell it a recalled memory helped or misled, and it re-ranks what comes back next. Shared rooms for multi-agent work. One key or OAuth across Claude Code, Cursor, VS Code and ChatGPT. MIT, in the official MCP Registry.
Provenance
2026-09-29: Package provenance attestation detected
|
A | 26 |
2026-10-03
|
69 | 84.6 was 79.6 ▲15.5 |
| =92 | ▼28 |
swimmwatch/cloakbrowser-mcp
⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.
Rank +1
2026-10-03: Rank dropped 28 spots (#64 → #92)
|
A | 72 |
2026-10-01
|
68 | 84.5 was 78.8 — |
| =92 | ▼2 |
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.
Rank
2026-09-26: Rank dropped 13 spots (#92 → #105)
|
A | 206 |
2026-10-02
|
199 | 84.5 was 80.1 ▲1.0 |
| 94 | ▲10 |
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.
Rank
2026-10-03: Rank rose 10 spots (#104 → #94)
|
A | 526 |
2026-10-03
|
21 | 84.3 was 79.3 ▼0.2 |
| 95 | ▲1 |
mistralai/mistral-vibe
Minimal CLI coding agent by Mistral
Rank
2026-09-26: Rank dropped 24 spots (#58 → #82)
|
A | 5.0k |
2026-09-29
|
9? | 84.2 was 80.1 ▼0.8 |
| 96 | ▼1 | traceloop/openllmetry Open-source observability for your GenAI or LLM application, based on OpenTelemetry | A | 7.5k |
2026-09-29
|
8? | 84.1 was 82.0 ▲0.2 |
| =97 | ▲1 |
langchain-ai/langchain
The agent engineering platform.
Rank
2026-10-01: Rank rose 11 spots (#110 → #99)
|
A | 147.4k |
2026-10-03
|
192 | 83.9 was 77.9 ▲0.8 |
| =97 | ▼6 | artokun/comfyui-mcp Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55… | A | 781 |
2026-10-02
|
116 | 83.9 was 79.7 ▼0.4 |
| =99 | ▼2 | ClickHouse/mcp-clickhouse Connect ClickHouse to your AI assistants. | A | 879 |
2026-10-01
|
13 | 83.8 was 83.1 ▼0.3 |
| =99 | ▲17 |
oomkapwn/enquire-mcp
The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.
Rank +2
2026-10-03: Rank rose 17 spots (#117 → #100)
|
A | 33 |
2026-10-03
|
30 | 83.8 was 77.8 ▼0.5 |
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
Better Notion MCP
repository is archived
Better Email MCP
repository is archived
Dynatrace MCP
repository is archived
Storybook MCP Addon
repository is archived
Claude Code
no declared license (GitHub license field is null)