AI Trust Registry for open-source AI agent projects.
Independent trust scores for 1371 open-source AI agent projects and 371 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 |
2026-10-10
|
260 | 96.3 was 95.7 ▼0.1 |
| 2 | = |
modelcontextprotocol/typescript-sdk
The official TypeScript SDK for Model Context Protocol servers and clients
Provenance +4
2026-10-08: Package provenance attestation detected
|
A | 13.6k |
2026-10-08
|
49 | 94.5 was 92.1 ▲26.2 |
| 3 | = | langchain-ai/langgraph Build resilient agents. | A | 43.0k |
2026-10-11
|
81 | 94.2 was 93.5 ▲1.1 |
| 4 | = | openai/openai-agents-js A lightweight, powerful framework for multi-agent workflows and voice agents | A | 3.9k |
2026-10-10
|
139 | 94.1 was 93.8 ▲0.2 |
| 5 | = |
modelcontextprotocol/python-sdk
The official Python SDK for Model Context Protocol servers and clients
Provenance +4
2026-10-08: Package provenance attestation detected
|
A | 24.5k |
2026-10-05
|
32 | 93.5 was 91.6 ▲24.0 |
| 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 | 27.2k |
2026-10-11
|
618 | 92.9 was 89.9 ▼3.3 |
| 7 | = | 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 | 25.9k |
2026-10-11
|
635 | 92.6 was 93.6 ▲0.4 |
| 8 | = | mobile-next/mobile-mcp Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices) | A | 8.9k |
2026-10-10
|
50 | 92.3 was 89.4 ▼0.7 |
| =9 | = | 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 | 845 |
2026-10-11
|
1137 | 91.7 was 90.4 ▼0.5 |
| =9 | ▲1 | livekit/agents A framework for building realtime voice AI agents 🤖🎙️📹 | A | 14.7k |
2026-10-11
|
190 | 91.7 was 90.0 ▲0.1 |
| 11 | ▲1 | microsoft/playwright-mcp Playwright MCP server | A | 38.0k |
2026-10-08
|
19 | 91.6 was 88.4 ▲0.4 |
| =12 | ▲5 | 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 | 46.3k |
2026-10-11
|
631 | 91.5 was 87.8 ▼1.5 |
| =12 | ▼3 | modelcontextprotocol/inspector Visual testing tool for MCP servers | A | 11.1k |
2026-10-08
|
750 | 91.5 was 87.9 ▲0.2 |
| =12 | = | 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 | 206.9k |
2026-10-11
|
1396 | 91.5 was 93.1 ▲1.4 |
| =12 | = | cline/cline Autonomous coding agent as an SDK, IDE extension, or CLI assistant. | A | 70.1k |
2026-10-11
|
304 | 91.5 was 91.0 ▼0.3 |
| 16 | ▼3 | openai/openai-agents-python A lightweight, powerful framework for multi-agent workflows | A | 30.0k |
2026-10-08
|
236 | 91.4 was 94.8 ▼0.2 |
| 17 | ▼1 | openclaw/openclaw The AI that really does things. Any OS. Any Platform. The lobster way. 🦞 | A | 391.7k |
2026-10-11
|
15703 | 91.1 was 91.2 ▼0.1 |
| 18 | = | 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 |
2026-10-10
|
259 | 90.4 was 88.9 — |
| 19 | = |
browser-use/browser-harness
Browser Harness | Self-healing harness that enables LLMs to complete any task.
Rank +8
2026-10-09: Rank rose 81 spots (#99 → #18)
|
A | 18.4k |
2026-10-09
|
100 | 90.3 was 86.5 ▲2.3 |
| =20 | = |
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.
Provenance +3
2026-10-05: Package provenance attestation detected
|
A | 5.3k |
2026-10-11
|
299 | 90.0 was 86.5 ▲13.5 |
| =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 | 276.7k |
2026-10-11
|
894 | 90.0 was 88.3 ▲2.0 |
| 22 | ▼1 | openai/codex Lightweight coding agent that runs in your terminal | A | 128.6k |
2026-10-11
|
1480 | 89.9 was 86.4 ▼0.1 |
| 23 | ▲1 | huggingface/lerobot 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning | A | 28.1k |
2026-10-10
|
64 | 89.7 was 89.7 ▼0.2 |
| =24 | ▲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 | 28.3k |
2026-10-11
|
464 | 89.6 was 90.2 — |
| =24 | ▲1 | docling-project/docling Get your documents ready for gen AI | A | 68.7k |
2026-10-11
|
222 | 89.6 was 89.1 ▼0.1 |
| =26 | ▲1 | 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 | 8.7k |
2026-10-11
|
851 | 89.5 was 87.2 ▼0.9 |
| =26 | ▼4 | a2aproject/A2A Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications. | A | 26.1k |
2026-10-08
|
19 | 89.5 was 90.1 ▲0.4 |
| =26 | = | cloudflare/agents Build and deploy AI Agents on Cloudflare | A | 5.8k |
2026-10-09
|
171 | 89.5 was 86.6 ▼0.2 |
| 29 | = | 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 | 10.5k |
2026-10-09
|
90 | 89.2 was 86.0 ▲0.4 |
| =30 | ▲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 | 1.2k |
2026-10-11
|
403 | 89.1 was 88.2 ▲0.2 |
| =30 | ▲1 | 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 | 3.8k |
2026-10-10
|
256 | 89.1 was 84.8 ▼0.1 |
| 32 | ▼2 | ihor-sokoliuk/mcp-searxng Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client | A | 1.3k |
2026-10-10
|
67 | 89.0 was 84.3 ▲0.3 |
| =33 | ▲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.
Rank +3
2026-10-09: Rank rose 19 spots (#57 → #38)
|
A | 122 |
2026-10-11
|
380 | 88.9 was 86.8 ▲2.9 |
| =33 | ▼1 | 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 | 25.6k |
2026-10-10
|
93 | 88.9 was 88.3 ▲0.1 |
| 35 | = | software-mansion/argent An agentic toolkit to control, debug, and profile iOS and Android apps. Made by Software Mansion. | A | 3.0k |
2026-10-09
|
77 | 88.7 was 84.3 ▼0.5 |
| 36 | = | agentscope-ai/ReMe ReMe: Memory Management Kit for Agents - Remember Me, Refine Me. | A | 3.6k |
2026-10-09
|
41 | 88.5 was 86.1 ▼0.1 |
| =37 | ▲1 | volcengine/OpenViking Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | A | 39.6k |
2026-10-11
|
407 | 88.3 was 90.2 ▲0.3 |
| =37 | ▲1 |
pydantic/pydantic-ai
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
Rank
2026-10-06: Rank dropped 12 spots (#26 → #38)
|
A | 20.5k |
2026-10-11
|
851 | 88.3 was 89.9 ▼1.0 |
| =37 | ▼2 | firecrawl/firecrawl Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥 | A | 190.3k |
2026-10-10
|
259 | 88.3 was 90.8 ▲0.1 |
| 40 | = | supabase/mcp Connect Supabase to your AI assistants | A | 2.9k |
2026-10-09
|
14 | 88.1 was 83.4 ▼0.2 |
| =41 | ▲1 |
morluto/rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Rank +7
2026-10-09: Rank rose 19 spots (#66 → #47)
|
A | 81.0k |
2026-10-11
|
1531 | 88.0 was 84.2 ▲6.7 |
| =41 | ▲2 | mongodb-js/mongodb-mcp-server A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters. | A | 1.1k |
2026-10-11
|
61 | 88.0 was 84.3 ▼0.6 |
| =43 | ▼2 | cap-js/mcp-server MCP server for AI-assisted development of CAP applications | A | 113 |
2026-10-10
|
24 | 87.9 was 83.2 ▲0.7 |
| =43 | ▲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 |
2026-10-11
|
492 | 87.9 was 83.2 ▼2.3 |
| =43 | ▲1 |
QwenLM/qwen-code
An open-source AI coding agent that lives in your terminal.
Rank
2026-10-10: Rank dropped 16 spots (#30 → #46)
|
A | 28.4k |
2026-10-11
|
1047 | 87.9 was 85.4 — |
| 46 | ▲1 | homeassistant-ai/ha-mcp The Unofficial and Awesome Home Assistant MCP Server | A | 5.0k |
2026-10-11
|
394 | 87.8 was 84.9 — |
| =47 | ▲1 | thesysdev/openui The Open Standard for Generative UI | A | 10.7k |
2026-10-11
|
102 | 87.7 was 85.9 — |
| =47 | ▲1 | vercel-labs/agent-browser Browser automation CLI for AI agents | A | 43.8k |
2026-10-11
|
32 | 87.7 was 86.1 — |
| 49 | ▲1 | CursorTouch/Windows-MCP MCP Server for Computer Use in Windows | A | 8.6k |
2026-10-10
|
31 | 87.6 was 83.7 ▲0.6 |
| 50 | ▲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 | 212 |
2026-10-10
|
150 | 87.5 was 82.1 ▼0.2 |
| =51 | ▲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.
Rank +1
2026-10-06: Rank rose 45 spots (#93 → #48)
|
A | 207 |
2026-10-08
|
197 | 87.4 was 84.3 ▲2.9 |
| =51 | ▲1 | arc-mcp/arc-1 | A | 215 |
2026-10-11
|
136 | 87.4 was 82.4 ▲0.1 |
| =51 | ▲1 | agno-agi/agno Build, run, and manage agent platforms. | A | 42.7k |
2026-10-11
|
130 | 87.4 was 88.0 — |
| =54 | ▲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 | 16 |
2026-10-10
|
121 | 87.2 was 81.7 ▲0.2 |
| =54 | ▲1 | zereight/gitlab-mcp First gitlab mcp for you, building together | A | 2.0k |
2026-10-10
|
272 | 87.2 was 83.2 — |
| =56 | ▲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…
Mcp Status Changed +1
2026-10-07: Detected MCP server support changed: implemented → none
|
A | 15.6k |
2026-10-10
|
23 | 87.1 was 88.0 ▼0.9 |
| =56 | ▲1 | getzep/graphiti Build Real-Time Knowledge Graphs for AI Agents | A | 31.6k |
2026-10-10
|
35 | 87.1 was 87.0 ▲0.8 |
| =58 | ▲2 | Skyvern-AI/skyvern Automate browser based workflows with AI | A | 23.2k |
2026-10-11
|
284 | 87.0 was 89.2 — |
| =58 | = | punkpeye/fastmcp A TypeScript framework for building MCP servers. | A | 3.3k |
2026-10-04
|
45 | 87.0 was 81.8 ▼0.6 |
| =60 | ▲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 | 509 |
2026-10-11
|
76 | 86.9 was 83.2 ▼0.9 |
| =60 | ▲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 +3
2026-10-09: Rank dropped 16 spots (#47 → #63)
|
A | 1.0k |
2026-10-11
|
165 | 86.9 was 81.7 ▼1.0 |
| 62 | ▲4 | 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 | 55 |
2026-10-09
|
49 | 86.8 was 83.0 ▲0.8 |
| =63 | = | 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 |
2026-10-10
|
206 | 86.7 was 82.2 ▲0.2 |
| =63 | = |
modelcontextprotocol/ext-apps
Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers
Rank +1
2026-10-08: Rank dropped 21 spots (#29 → #50)
|
A | 2.9k |
2026-09-25
|
8 | 86.7 was 81.4 ▼2.6 |
| =63 | = | triggerdotdev/trigger.dev Trigger.dev – build and deploy durable AI agents and workflows | A | 16.5k |
2026-10-10
|
270 | 86.7 was 84.4 ▼0.3 |
| =63 | ▼23 |
lancedb/lancedb
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
Rank +4
2026-10-11: Rank dropped 23 spots (#43 → #66)
|
A | 11.6k |
2026-10-11
|
173 | 86.7 was 88.5 ▲14.0 |
| =63 | ▲1 |
milind-soni/OpenMausBot
Open-source Grok Bot alternative with a virtual machine that bots can use
Scorecard +4
2026-10-10: OSSF Scorecard: 4.2/10
|
A | 4.4k |
2026-10-11
|
2197 | 86.7 was 81.0 |
| 68 | ▼1 | botpress/botpress The open-source hub to build & deploy GPT/LLM Agents ⚡️ | A | 14.9k |
2026-10-09
|
28 | 86.4 was 84.6 ▼0.2 |
| 69 | ▲4 |
traceloop/openllmetry
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
Rank
2026-10-06: Rank rose 22 spots (#92 → #70)
|
A | 7.5k |
2026-10-11
|
14 | 86.3 was 85.2 ▲1.9 |
| =70 | ▼1 | UI5/mcp-server The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework. | A | 101 |
2026-10-09
|
25 | 86.2 was 80.7 ▼0.3 |
| =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 | 1.0k |
2026-10-08
|
25 | 86.2 was 81.7 ▼0.2 |
| =72 | = |
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.
Rank +1
2026-10-08: Rank dropped 19 spots (#54 → #73)
|
A | 288 |
2026-10-11
|
297 | 86.1 was 81.6 ▼1.6 |
| =72 | ▼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 | 67.0k |
2026-10-09
|
46 | 86.1 was 88.4 — |
| =72 | = | 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 |
2026-10-10
|
88 | 86.1 was 81.6 ▲0.3 |
| 75 | = | samuelgursky/davinci-resolve-mcp MCP server integration for DaVinci Resolve Studio | A | 3.5k |
2026-10-10
|
204 | 86.0 was 80.4 ▼0.3 |
| =76 | = |
swimmwatch/cloakbrowser-mcp
⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.
Rank
2026-10-04: Rank rose 18 spots (#92 → #74)
|
A | 164 |
2026-10-10
|
58 | 85.9 was 80.3 ▲0.3 |
| =76 | = | vectorize-io/hindsight Hindsight: Agent Memory That Learns | A | 48.2k |
2026-10-10
|
617 | 85.9 was 86.3 ▼0.1 |
| 78 | ▲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 +1
2026-10-09: Rank rose 11 spots (#90 → #79)
|
A | 32.0k |
2026-10-09
|
927 | 85.7 was 87.9 ▼0.2 |
| 79 | ▲1 | browserstack/mcp-server BrowserStack's Official MCP Server | A | 154 |
2026-10-09
|
205 | 85.6 was 79.6 ▼0.5 |
| 80 | ▲1 | 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 | 17.8k |
2026-10-09
|
35 | 85.5 was 81.6 ▲0.1 |
| =81 | ▲5 | AIOSAI/AIPass Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero. | A | 288 |
2026-10-11
|
153 | 85.4 was 83.1 ▲0.4 |
| =81 | = | boxlite-ai/boxlite The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud. | A | 2.5k |
2026-10-10
|
122 | 85.4 was 83.5 — |
| 83 | = | 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 | 13.4k |
2026-10-10
|
19 | 85.3 was 84.5 ▼0.3 |
| 84 | ▲1 | vespa-engine/vespa The AI search platform | A | 7.1k |
2026-10-11
|
681 | 85.2 was 85.5 ▲0.4 |
| 85 | ▼1 | StuMason/coolify-mcp MCP server for Coolify — 42 optimized tools for managing self-hosted PaaS through AI assistants | A | 611 |
2026-10-11
|
60 | 85.1 was 80.1 ▼0.7 |
| =86 | ▲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 | 543 |
2026-10-09
|
68 | 85.0 was 81.2 ▲0.2 |
| =86 | ▲3 |
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.
New
2026-10-09: First tracked at rank #93
|
A | 2.4k |
2026-10-11
|
596 | 85.0 was 80.5 |
| =86 | = |
containers/kubernetes-mcp-server
Model Context Protocol (MCP) server for Kubernetes and OpenShift
Rank
2026-10-09: Rank dropped 11 spots (#78 → #89)
|
A | 2.2k |
2026-10-09
|
28 | 85.0 was 79.0 ▼0.2 |
| 89 | ▲2 | pvliesdonk/markdown-vault-mcp Generic markdown vault MCP with hybrid search | A | 34 |
2026-10-11
|
161 | 84.9 was 79.7 ▲1.1 |
| =90 | ▲3 | 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. | A | 18 |
2026-10-03
|
289 | 84.8 was 81.6 ▲0.1 |
| =90 | ▼2 | pipecat-ai/pipecat Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community. | A | 16.3k |
2026-10-11
|
940 | 84.8 was 85.5 ▼0.6 |
| =90 | ▲4 |
HKUDS/LightRAG
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
Rank
2026-10-10: Rank dropped 10 spots (#86 → #96)
|
A | 40.1k |
2026-10-08
|
301 | 84.8 was 85.7 ▼0.4 |
| =90 | ▲4 |
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 |
2026-10-09
|
249 | 84.8 was 80.4 ▼1.1 |
| =94 | = |
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 +2
2026-10-10: Rank rose 10 spots (#104 → #94)
|
A | 114 |
2026-10-11
|
282 | 84.6 was 83.2 ▲0.2 |
| =94 | ▲3 | stripe/ai One-stop shop for building AI-powered products and businesses with Stripe. | A | 1.9k |
2026-10-11
|
32 | 84.6 was 79.9 ▼0.2 |
| =96 | ▲5 |
sparfenyuk/mcp-proxy
A bridge between Streamable HTTP and stdio MCP transports
Grade Changed +3
2026-10-10: Trust grade B → A
|
A | 2.8k |
2026-10-10
|
14 | 84.5 was 79.5 ▲9.8 |
| =96 | ▲2 |
punitarani/fli
Google Flights MCP, CLI and Python Library
Rank
2026-10-04: Rank rose 30 spots (#113 → #83)
|
A | 3.2k |
2026-09-20
|
35 | 84.5 was 78.5 ▼0.4 |
| =98 | ▲2 | JustinBeckwith/gongio-mcp MCP server for Gong.io - access calls, transcripts, and users | A | 21 |
2026-10-10
|
11 | 84.4 was 78.4 ▲0.4 |
| =98 | ▼21 |
mistralai/mistral-vibe
Minimal CLI coding agent by Mistral
Rank +1
2026-10-11: Rank dropped 21 spots (#78 → #99)
|
A | 5.1k |
2026-10-09
|
9? | 84.4 was 80.4 ▲0.2 |
| =100 | ▲2 |
wandb/weave
Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.
Rank
2026-10-07: Rank dropped 10 spots (#87 → #97)
|
A | 1.1k |
2026-10-10
|
74 | 84.1 was 85.5 ▼0.7 |
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
★ 40.1k
HVTrust
ComposioHQ/composio
Tooling and context management for AI agents
★ 30.5k
HVTrust
deepset-ai/haystack
Open-source AI orchestration framework
★ 26.7k
HVTrust
AIOSAI/AIPass
Persistent workspace for AI agents
★ 288
HVTrust
sjkim1127/Reversecore_MCP
Security-first MCP server for reverse engineering
★ 207
HVTrust
cacheplane/threadplane
Open-source thread-plane for agents
★ 114
HVTrust
mcp-hangar/mcp-hangar
Policy enforcement plane for MCP calls
★ 18
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
Better Notion MCP
repository is archived
Better Email MCP
repository is archived
Dynatrace MCP
repository is archived
Claude Code
no declared license (GitHub license field is null)
Storybook MCP Addon
repository is archived