{"name":"Loadbay","description":"Catalog of harnesses for AI agents, across domains.","repo":"https://github.com/alessandrorodi/loadbay","count":67,"domains":{"trading":"Trading","coding":"Coding & DevOps","browser":"Browser & computer","productivity":"Productivity","data":"Data & search","social":"Social & comms","health":"Health","science":"Research & science","gaming":"Gaming","media":"Voice & media","robotics":"Robotics"},"traits":{"mcp":"Exposes an MCP server","keys":"Needs API keys / auth","sandbox":"Runs sandboxed","guard":"Guardrails / limits"},"harnesses":[{"slug":"dbhub","name":"DBHub","author":"bytebase","domain":"data","integrations":["Postgres","MySQL"],"language":"TypeScript","license":"MIT","stars":3000,"traits":["mcp","oss","keys"],"summary":"A zero-dependency database MCP server for Postgres, MySQL, SQL Server, and more — query your data in natural language.","repo":"https://github.com/bytebase/dbhub","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/dbhub","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"mindsearch","name":"MindSearch","author":"InternLM","domain":"data","integrations":["Web"],"language":"Python","license":"Apache-2.0","stars":6900,"traits":["oss","keys"],"summary":"An open multi-agent web-search framework, in the spirit of Perplexity Pro, that plans queries and synthesizes answers.","repo":"https://github.com/InternLM/MindSearch","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/mindsearch","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"mcp-filesystem-server","name":"mcp-filesystem-server","author":"mark3labs","domain":"data","integrations":["Filesystem"],"language":"Go","license":"MIT","stars":653,"traits":["mcp","oss"],"summary":"A filesystem MCP server — give an agent scoped read/write access to files and directories.","repo":"https://github.com/mark3labs/mcp-filesystem-server","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/mcp-filesystem-server","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"mem0","name":"mem0","author":"mem0ai","domain":"data","integrations":["OpenAI","Qdrant","Neo4j"],"language":"Python","license":"Apache-2.0","stars":58796,"traits":["mcp","oss","keys"],"summary":"Universal memory layer that gives AI agents persistent long-term memory across sessions via SDK and MCP.","repo":"https://github.com/mem0ai/mem0","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/mem0","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"letta","name":"letta","author":"letta-ai","domain":"data","integrations":["OpenAI","PostgreSQL"],"language":"Python","license":"Apache-2.0","stars":23380,"traits":["oss","keys"],"summary":"Platform for stateful agents with advanced memory (formerly MemGPT) that learn and self-improve over time.","repo":"https://github.com/letta-ai/letta","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/letta","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"graphiti","name":"graphiti","author":"getzep","domain":"data","integrations":["Neo4j","OpenAI"],"language":"Python","license":"Apache-2.0","stars":27546,"traits":["mcp","oss","keys"],"summary":"Framework for building real-time temporal knowledge graphs as memory for AI agents, with an MCP server.","repo":"https://github.com/getzep/graphiti","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/graphiti","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"cognee","name":"cognee","author":"topoteretes","domain":"data","integrations":["Neo4j","Qdrant"],"language":"Python","license":"Apache-2.0","stars":17879,"traits":["mcp","oss","keys"],"summary":"Open-source AI memory platform giving agents persistent long-term memory via a self-hosted knowledge-graph engine.","repo":"https://github.com/topoteretes/cognee","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/cognee","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"qdrant","name":"qdrant","author":"qdrant","domain":"data","integrations":["Qdrant"],"language":"Rust","license":"Apache-2.0","stars":32404,"traits":["oss"],"summary":"High-performance, massive-scale vector database and vector search engine with REST and gRPC APIs.","repo":"https://github.com/qdrant/qdrant","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/qdrant","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"mcp-server-qdrant","name":"mcp-server-qdrant","author":"qdrant","domain":"data","integrations":["Qdrant"],"language":"Python","license":"Apache-2.0","stars":1436,"traits":["mcp","oss","keys"],"summary":"Official Qdrant MCP server exposing vector storage and semantic search as a memory layer for agents.","repo":"https://github.com/qdrant/mcp-server-qdrant","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/mcp-server-qdrant","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"chroma","name":"chroma","author":"chroma-core","domain":"data","integrations":["Chroma"],"language":"Rust","license":"Apache-2.0","stars":28460,"traits":["mcp","oss"],"summary":"Open-source embedding database and search infrastructure for building AI apps with retrieval and memory.","repo":"https://github.com/chroma-core/chroma","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/chroma","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"milvus","name":"milvus","author":"milvus-io","domain":"data","integrations":["Milvus"],"language":"Go","license":"Apache-2.0","stars":44821,"traits":["oss"],"summary":"High-performance, cloud-native vector database built for scalable vector ANN search over billions of vectors.","repo":"https://github.com/milvus-io/milvus","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/milvus","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"weaviate","name":"weaviate","author":"weaviate","domain":"data","integrations":["Weaviate"],"language":"Go","license":"BSD-3-Clause","stars":16340,"traits":["oss","keys"],"summary":"Open-source vector database storing objects and vectors, combining vector search with structured filtering.","repo":"https://github.com/weaviate/weaviate","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/weaviate","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"lancedb","name":"lancedb","author":"lancedb","domain":"data","integrations":["LanceDB"],"language":"Rust","license":"Apache-2.0","stars":10630,"traits":["oss"],"summary":"Developer-friendly embedded retrieval library and vector database for multimodal AI search.","repo":"https://github.com/lancedb/lancedb","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/lancedb","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"txtai","name":"txtai","author":"neuml","domain":"data","integrations":["Hugging Face"],"language":"Python","license":"Apache-2.0","stars":12668,"traits":["oss"],"summary":"All-in-one embeddings framework for semantic search, RAG, and language-model workflows over your own data.","repo":"https://github.com/neuml/txtai","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/txtai","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"tavily-mcp","name":"tavily-mcp","author":"tavily-ai","domain":"data","integrations":["Tavily"],"language":"JavaScript","license":"MIT","stars":2110,"traits":["mcp","oss","keys"],"summary":"Production MCP server giving agents real-time web search, extract, map, and crawl via the Tavily API.","repo":"https://github.com/tavily-ai/tavily-mcp","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/tavily-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"exa-mcp-server","name":"exa-mcp-server","author":"exa-labs","domain":"data","integrations":["Exa"],"language":"TypeScript","license":"MIT","stars":4588,"traits":["mcp","oss","keys"],"summary":"MCP server letting agents perform web search and crawling through the Exa neural search API.","repo":"https://github.com/exa-labs/exa-mcp-server","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/exa-mcp-server","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"searxng","name":"searxng","author":"searxng","domain":"data","integrations":["SearXNG"],"language":"Python","license":"AGPL-3.0","stars":32252,"traits":["oss"],"summary":"Free, self-hostable metasearch engine that aggregates results from many services without tracking users.","repo":"https://github.com/searxng/searxng","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/searxng","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"graphrag","name":"graphrag","author":"microsoft","domain":"data","integrations":["OpenAI","Azure"],"language":"Python","license":"MIT","stars":33815,"traits":["oss","keys"],"summary":"Modular graph-based retrieval-augmented generation system that builds knowledge graphs from documents for agent queries.","repo":"https://github.com/microsoft/graphrag","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/graphrag","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"docling","name":"docling","author":"docling-project","domain":"data","integrations":["Hugging Face"],"language":"Python","license":"MIT","stars":61748,"traits":["mcp","oss"],"summary":"Document parsing and ingestion toolkit that converts PDFs, Office files, and images into structured data for gen AI.","repo":"https://github.com/docling-project/docling","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/docling","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"hexstrike-ai","name":"hexstrike-ai","author":"0x4m4","domain":"data","integrations":["Nmap","Burp"],"language":"Python","license":"MIT","stars":9678,"traits":["mcp","oss"],"summary":"MCP server that lets AI agents autonomously run 150+ cybersecurity tools for pentesting, vuln discovery, and bug-bounty automation.","repo":"https://github.com/0x4m4/hexstrike-ai","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/hexstrike-ai","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"pentestgpt","name":"PentestGPT","author":"GreyDGL","domain":"data","integrations":["OpenAI","LangChain"],"language":"Python","license":"MIT","stars":13783,"traits":["oss","keys"],"summary":"Automated penetration-testing agentic framework powered by LLMs that guides and runs offensive-security workflows.","repo":"https://github.com/GreyDGL/PentestGPT","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/pentestgpt","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"ai-infra-guard","name":"AI-Infra-Guard","author":"Tencent","domain":"data","integrations":["MCP"],"language":"Python","license":"Apache-2.0","stars":3919,"traits":["oss","guard"],"summary":"Full-stack AI red-teaming platform for agent scan, MCP scan, AI infra scan, and LLM jailbreak evaluation.","repo":"https://github.com/Tencent/AI-Infra-Guard","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/ai-infra-guard","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"snyk-agent-scan","name":"agent-scan","author":"snyk","domain":"data","integrations":["MCP"],"language":"Python","license":"Apache-2.0","stars":2590,"traits":["oss","guard"],"summary":"Security scanner for AI agents, MCP servers, and agent skills that detects vulnerabilities and misconfigurations.","repo":"https://github.com/snyk/agent-scan","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/snyk-agent-scan","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"llama-index","name":"llama_index","author":"run-llama","domain":"data","integrations":["OpenAI","Anthropic"],"language":"Python","license":"MIT","stars":50197,"traits":["oss","keys"],"summary":"Data framework for building document agents and RAG pipelines that connect LLMs to private and external data sources.","repo":"https://github.com/run-llama/llama_index","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/llama-index","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"haystack","name":"haystack","author":"deepset-ai","domain":"data","integrations":["OpenAI"],"language":"Python","license":"Apache-2.0","stars":25592,"traits":["oss","keys"],"summary":"Orchestration framework for production LLM applications with modular pipelines for retrieval, RAG, and agent workflows.","repo":"https://github.com/deepset-ai/haystack","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/haystack","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"mcp-google-map","name":"mcp-google-map","author":"cablate","domain":"data","integrations":["Google Maps"],"language":"TypeScript","license":"MIT","stars":350,"traits":["mcp","oss","keys"],"summary":"MCP server for Google Maps including geocoding, place search, directions, and distance calculations.","repo":"https://github.com/cablate/mcp-google-map","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/mcp-google-map","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"brave-search-mcp-server","name":"brave-search-mcp-server","author":"brave","domain":"data","integrations":["Brave Search"],"language":"TypeScript","license":"MIT","stars":1197,"traits":["mcp","oss","keys"],"summary":"Official Brave Search MCP server providing web, image, video, news, and local search.","repo":"https://github.com/brave/brave-search-mcp-server","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/brave-search-mcp-server","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"perplexity-mcp","name":"modelcontextprotocol","author":"perplexityai","domain":"data","integrations":["Perplexity"],"language":"TypeScript","license":"MIT","stars":2315,"traits":["mcp","oss","keys"],"summary":"Official Perplexity MCP server that gives AI assistants web-wide search and answers through the Perplexity API.","repo":"https://github.com/perplexityai/modelcontextprotocol","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/perplexity-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"crawl4ai","name":"crawl4ai","author":"unclecode","domain":"data","integrations":["Playwright"],"language":"Python","license":"Apache-2.0","stars":68744,"traits":["oss"],"summary":"Open-source LLM-friendly web crawler and scraper that outputs clean markdown and structured data for agents.","repo":"https://github.com/unclecode/crawl4ai","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/crawl4ai","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"scrapegraph-ai","name":"Scrapegraph-ai","author":"ScrapeGraphAI","domain":"data","integrations":["LangChain"],"language":"Python","license":"MIT","stars":27293,"traits":["oss","keys"],"summary":"AI-powered Python scraper that uses LLMs and graph pipelines to extract data from websites and documents.","repo":"https://github.com/ScrapeGraphAI/Scrapegraph-ai","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/scrapegraph-ai","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"markitdown","name":"markitdown","author":"microsoft","domain":"data","integrations":["LLM"],"language":"Python","license":"MIT","stars":155123,"traits":["oss"],"summary":"Python tool that converts Office documents, PDFs, and other files to Markdown for LLM ingestion.","repo":"https://github.com/microsoft/markitdown","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/markitdown","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"unstructured","name":"unstructured","author":"Unstructured-IO","domain":"data","integrations":["LangChain","LlamaIndex"],"language":"Python","license":"Apache-2.0","stars":14955,"traits":["oss"],"summary":"Open-source ETL library that transforms complex documents into clean structured data for language models.","repo":"https://github.com/Unstructured-IO/unstructured","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/unstructured","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"firecrawl","name":"Firecrawl","author":"firecrawl","domain":"data","integrations":["Web"],"language":"TypeScript","license":"AGPL-3.0","stars":134000,"traits":["oss","keys"],"summary":"Search, scrape, and crawl the web at scale and get clean, structured content. The data layer behind a lot of agents.","repo":"https://github.com/firecrawl/firecrawl","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/firecrawl","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"ragflow","name":"RAGFlow","author":"infiniflow","domain":"data","integrations":["Elasticsearch","OpenAI","Ollama"],"language":"Python","license":"Apache-2.0","stars":83000,"traits":["oss"],"summary":"Open-source RAG engine built on deep document understanding, with grounded citations and an end-to-end retrieval pipeline.","repo":"https://github.com/infiniflow/ragflow","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/ragflow","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"faiss","name":"Faiss","author":"facebookresearch","domain":"data","integrations":["PyTorch","NumPy"],"language":"C++","license":"MIT","stars":40000,"traits":["oss"],"summary":"Meta library for efficient similarity search and clustering of dense vectors; the de-facto ANN index under many vector DBs.","repo":"https://github.com/facebookresearch/faiss","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/faiss","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"pgvector","name":"pgvector","author":"pgvector","domain":"data","integrations":["Postgres","Supabase"],"language":"C","license":"PostgreSQL","stars":21800,"traits":["oss"],"summary":"Postgres extension adding vector types and HNSW/IVFFlat similarity search, for vector retrieval inside a relational DB.","repo":"https://github.com/pgvector/pgvector","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/pgvector","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"scrapy","name":"Scrapy","author":"scrapy","domain":"data","integrations":["Playwright"],"language":"Python","license":"BSD-3-Clause","stars":62000,"traits":["oss"],"summary":"Fast asynchronous Python framework for large-scale web crawling and structured data extraction.","repo":"https://github.com/scrapy/scrapy","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/scrapy","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"crawlee","name":"Crawlee","author":"apify","domain":"data","integrations":["Playwright","Puppeteer"],"language":"TypeScript","license":"Apache-2.0","stars":23800,"traits":["oss"],"summary":"Web scraping and browser-automation library (Node and Python) built to extract data for AI, LLMs, and RAG.","repo":"https://github.com/apify/crawlee","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/crawlee","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"mineru","name":"MinerU","author":"opendatalab","domain":"data","integrations":["LlamaIndex","LangChain"],"language":"Python","license":"AGPL-3.0","stars":67000,"traits":["oss"],"summary":"Converts PDFs and documents into machine-readable Markdown and JSON, extracting formulas, tables, and reading order for RAG.","repo":"https://github.com/opendatalab/MinerU","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/mineru","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"marker","name":"Marker","author":"datalab-to","domain":"data","integrations":["Surya OCR","LlamaIndex"],"language":"Python","license":"GPL-3.0","stars":36000,"traits":["oss"],"summary":"Fast, high-accuracy converter of PDF, EPUB, and docs to Markdown and JSON with table, equation, and layout handling.","repo":"https://github.com/datalab-to/marker","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/marker","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"meilisearch","name":"Meilisearch","author":"meilisearch","domain":"data","integrations":["LangChain","OpenAI"],"language":"Rust","license":"MIT","stars":58000,"traits":["oss"],"summary":"Fast, typo-tolerant open-source search engine with built-in hybrid keyword and vector/semantic search.","repo":"https://github.com/meilisearch/meilisearch","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/meilisearch","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"typesense","name":"Typesense","author":"typesense","domain":"data","integrations":["LangChain","OpenAI"],"language":"C++","license":"GPL-3.0","stars":26000,"traits":["oss"],"summary":"Open-source typo-tolerant search engine with native vector and hybrid semantic search, a lightweight retrieval backend.","repo":"https://github.com/typesense/typesense","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/typesense","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"anythingllm","name":"AnythingLLM","author":"Mintplex-Labs","domain":"data","integrations":["Ollama","OpenAI","LanceDB"],"language":"JavaScript","license":"MIT","stars":61000,"traits":["oss","mcp","keys"],"summary":"All-in-one app turning documents into a private RAG chatbot, bundling ingestion, vector storage, and retrieval; MCP-compatible.","repo":"https://github.com/Mintplex-Labs/anything-llm","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/anythingllm","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"integuru","name":"Integuru","author":"Integuru-AI","domain":"data","integrations":["HTTP","Browser"],"language":"Python","license":"AGPL-3.0","stars":4620,"traits":["oss","keys"],"summary":"AI agent that reverse-engineers a platform's internal APIs from browser traffic to build permissionless integrations.","repo":"https://github.com/Integuru-AI/Integuru","community":false,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/integuru","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"turso","name":"Turso","author":"tursodatabase","domain":"data","integrations":["Claude Code","Claude Desktop","Cursor","Python","Node.js","Go","Java","Rust"],"language":null,"license":"MIT","stars":21117,"traits":["oss"],"summary":"A modern SQLite-compatible in-process database written in Rust with a built-in MCP server that exposes nine tools (query, insert, update, schema management) to any AI agent. Run `tursodb your_database.db --mcp` to give Claude Code, Claude Desktop, or Cursor full read-write access to structured data.","repo":"https://github.com/tursodatabase/turso","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/turso","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"memanto","name":"memanto","author":"moorcheh-ai","domain":"data","integrations":["CrewAI","LangChain","RAG","semantic memory","vector search"],"language":null,"license":"MIT","stars":1303,"traits":["oss"],"summary":"Pluggable long-term memory layer for AI agents with semantic and episodic recall, designed to integrate directly with CrewAI, LangChain, and other agent frameworks. Agents read and write memories through a simple API that supports RAG-based retrieval and stateful multi-session continuity.","repo":"https://github.com/moorcheh-ai/memanto","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/memanto","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"cocoindex","name":"cocoindex","author":"cocoindex-io","domain":"data","integrations":["PostgreSQL","Pinecone","Qdrant","Python","Rust"],"language":null,"license":"Apache-2.0","stars":10563,"traits":["oss"],"summary":"Incremental data-indexing engine for long-horizon AI agents — keeps RAG pipelines and agent context always fresh by only reprocessing changed data from codebases, Slack, docs, and databases.","repo":"https://github.com/cocoindex-io/cocoindex","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/cocoindex","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"spiceai","name":"spiceai","author":"spiceai","domain":"data","integrations":["MCP","Claude Code","Cursor","PostgreSQL","Apache Iceberg","vLLM","Redis"],"language":null,"license":"Apache-2.0","stars":2968,"traits":["oss","keys"],"summary":"Portable Rust runtime that operates as an MCP server sidecar providing SQL query federation, hybrid vector/BM25 search, and LLM inference across 30+ data connectors, with text-to-SQL tools and agent skills for Claude Code and Cursor. Enables agents to query federated data sources at millisecond latency.","repo":"https://github.com/spiceai/spiceai","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/spiceai","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"hindsight","name":"Hindsight","author":"vectorize-io","domain":"data","integrations":["Python","TypeScript","Docker"],"language":null,"license":"MIT","stars":16906,"traits":["oss","keys"],"summary":"A biomimetic agent memory system that organizes long-term knowledge into worlds (facts), experiences, and mental models so agents can retain, recall, and reflect on information across sessions. Achieves state-of-the-art on LongMemEval and deploys via Docker, bare-metal, or embedded Python mode.","repo":"https://github.com/vectorize-io/hindsight","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/hindsight","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"open-seo","name":"open-seo","author":"every-app","domain":"data","integrations":["Claude Code","OpenClaw","Hermes","Google Search Console","DataForSEO"],"language":null,"license":"MIT","stars":2967,"traits":["oss","mcp","keys"],"summary":"An open-source SEO platform with an MCP server and pre-built agent skills for keyword research, rank tracking, and domain insights — agents connect via MCP or install skills to run full SEO workflows against DataForSEO and Google Search Console.","repo":"https://github.com/every-app/open-seo","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/open-seo","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"skills-for-fabric","name":"skills-for-fabric","author":"microsoft","domain":"data","integrations":["Microsoft Fabric","Azure","Claude Code","GitHub Copilot","Cursor"],"language":null,"license":"MIT","stars":717,"traits":["oss","mcp","keys"],"summary":"Reusable agent skills and MCP server configurations that let AI coding tools (Claude Code, GitHub Copilot, Cursor) query and operate Microsoft Fabric workloads including SQL, Spark, Power BI, and KQL endpoints via Azure credentials.","repo":"https://github.com/microsoft/skills-for-fabric","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/skills-for-fabric","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"firecrawl-mcp-server","name":"firecrawl-mcp-server","author":"firecrawl","domain":"data","integrations":["Firecrawl API","Claude Desktop","Cursor","Windsurf"],"language":null,"license":"MIT","stars":6832,"traits":["oss","mcp","keys"],"summary":"Official Firecrawl MCP Server that adds powerful web scraping, crawling, and search capabilities to Claude Desktop, Cursor, and other MCP clients via the Firecrawl API. Agents can crawl entire sites or search the web and receive clean Markdown output.","repo":"https://github.com/firecrawl/firecrawl-mcp-server","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/firecrawl-mcp-server","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"apify-mcp-server","name":"apify-mcp-server","author":"apify","domain":"data","integrations":["Claude Code","Claude.ai","Cursor","VS Code","Apify Actors"],"language":null,"license":"MIT","stars":1696,"traits":["oss","mcp","keys"],"summary":"Official Apify MCP server that gives AI agents access to thousands of ready-made web scrapers and automation Actors — extract data from social media, search engines, maps, and e-commerce sites via OAuth or API token.","repo":"https://github.com/apify/apify-mcp-server","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/apify-mcp-server","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"google-analytics-mcp","name":"google-analytics-mcp","author":"googleanalytics","domain":"data","integrations":["Google Analytics Admin API","Google Analytics Data API","MCP clients"],"language":null,"license":"Apache-2.0","stars":2604,"traits":["oss","mcp","keys"],"summary":"An official Google Analytics MCP server that enables language models to query Analytics account data and run reports through the Google Analytics Admin and Data APIs. Exposes tools for account summaries, standard reports, and real-time analytics.","repo":"https://github.com/googleanalytics/google-analytics-mcp","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/google-analytics-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"tabularis","name":"tabularis","author":"TabularisDB","domain":"data","integrations":["Claude","Cursor","Devin","PostgreSQL","MySQL","SQLite","DuckDB","ClickHouse","Redis","Firestore"],"language":null,"license":"Apache-2.0","stars":3676,"traits":["oss","mcp","keys"],"summary":"Desktop SQL workspace for 14+ databases—PostgreSQL, MySQL, SQLite, DuckDB, ClickHouse—with a built-in MCP server so Claude, Cursor, and Devin can query and manage databases directly.","repo":"https://github.com/TabularisDB/tabularis","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/tabularis","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"openmetadata","name":"OpenMetadata","author":"open-metadata","domain":"data","integrations":["Claude","AI assistants","Snowflake","BigQuery","Redshift","PostgreSQL","dbt"],"language":null,"license":"Apache-2.0","stars":14446,"traits":["oss","mcp","keys"],"summary":"Open Context Layer for Data and AI: an open platform for metadata management, data discovery, and semantic context that exposes an MCP server so AI agents can query and navigate enterprise data assets.","repo":"https://github.com/open-metadata/OpenMetadata","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/openmetadata","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"webclaw","name":"webclaw","author":"0xMassi","domain":"data","integrations":["Claude","Cursor","LangChain","Any MCP client","RAG pipelines"],"language":null,"license":"AGPL-3.0","stars":1712,"traits":["oss","mcp"],"summary":"Fast, local-first web content extraction Rust binary that scrapes, crawls, and converts web pages to structured Markdown; ships a CLI, REST API, and MCP server for LLM and agent pipelines.","repo":"https://github.com/0xMassi/webclaw","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/webclaw","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"openviking","name":"OpenViking","author":"volcengine","domain":"data","integrations":["Volcengine","OpenAI","Kimi","GLM","custom VLM/embedding providers"],"language":null,"license":"AGPL-3.0","stars":26574,"traits":["oss","keys"],"summary":"A unified context database for AI agents that manages memory, knowledge retrieval, and skills through a filesystem-like hierarchy with tiered loading (abstract summaries, overviews, full details). Reduces token consumption while improving retrieval accuracy via recursive directory-based search strategies.","repo":"https://github.com/volcengine/OpenViking","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/openviking","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"korean-law-mcp","name":"korean-law-mcp","author":"chrisryugj","domain":"data","integrations":["Claude Desktop","Cursor","Windsurf","Zed"],"language":null,"license":"MIT","stars":2203,"traits":["oss","mcp"],"summary":"MCP server wrapping 42 Korean Ministry of Government Legislation APIs into 10 tools for statutes, precedents, ordinances, and treaties. Includes citation hallucination verification, article impact graphs, and temporal law comparison.","repo":"https://github.com/chrisryugj/korean-law-mcp","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/korean-law-mcp","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"memvid","name":"memvid","author":"memvid","domain":"data","integrations":["Rust SDK","Python SDK","Node.js SDK","CLI"],"language":null,"license":"Apache-2.0","stars":15971,"traits":["oss"],"summary":"A serverless agent memory layer that packages data, embeddings, and search structures into portable .mv2 files for persistent long-term memory without databases. Supports vector similarity search, full-text search, and temporal queries via SDKs in Rust, Python, Node.js, and CLI.","repo":"https://github.com/memvid/memvid","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/memvid","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"open-deep-research","name":"Open Deep Research","author":"langchain-ai","domain":"data","integrations":["LangGraph","Tavily","OpenAI","Anthropic","MCP servers","Perplexity"],"language":null,"license":"MIT","stars":12105,"traits":["oss","mcp","keys"],"summary":"Open-source deep research agent built on LangGraph that autonomously searches, synthesizes, and generates comprehensive reports; supports MCP servers and works across many LLM providers and search APIs.","repo":"https://github.com/langchain-ai/open_deep_research","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/open-deep-research","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"openosint","name":"OpenOSINT","author":"OpenOSINT","domain":"data","integrations":["Claude","GPT-4","Ollama","Sherlock","Holehe","Maigret"],"language":null,"license":"MIT","stars":1112,"traits":["oss","mcp"],"summary":"AI-powered OSINT agent with an integrated MCP server exposing 16 intelligence-gathering tools including Sherlock, Holehe, and Maigret for authorized security research. Works with Claude, GPT-4, or local models via an interactive REPL or CLI.","repo":"https://github.com/OpenOSINT/OpenOSINT","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/openosint","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"kindly-web-search","name":"kindly-web-search","author":"Shelpuk-AI-Technology-Consulting","domain":"data","integrations":["Serper","Tavily","SearXNG","Claude Code","Codex","Cursor","GitHub Copilot","Hermes","OpenClaw"],"language":null,"license":"MIT","stars":359,"traits":["oss","mcp","keys"],"summary":"Web search MCP server for AI coding tools and agents, supporting Serper, Tavily, and SearXNG backends. Agents call it to search the web and retrieve full page content in a structured format, compatible with Claude Code, Codex, Cursor, and 40+ others.","repo":"https://github.com/Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/kindly-web-search","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"retentioneering-tools","name":"retentioneering-tools","author":"retentioneering","domain":"data","integrations":["Python","MCP server","Agent skills","Clickstream data","Product analytics platforms"],"language":null,"license":"Apache-2.0","stars":909,"traits":["oss","mcp"],"summary":"Python toolkit, MCP server, and agent skills for reproducible clickstream and event-log analytics. AI agents connect via MCP to build customer journey maps, run behavioral segmentation, A/B tests, and Markov chain simulations over product event data.","repo":"https://github.com/retentioneering/retentioneering-tools","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/retentioneering-tools","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"pageindex","name":"PageIndex","author":"VectifyAI","domain":"data","integrations":["OpenAI Agents SDK","Claude","LiteLLM","MCP clients"],"language":null,"license":"MIT","stars":34522,"traits":["oss","mcp","keys"],"summary":"Vectorless RAG system that builds hierarchical tree indexes from documents and uses LLM reasoning for context-aware retrieval, eliminating vector databases and chunking. Exposes an MCP server for agent integration and supports multi-LLM backends via LiteLLM.","repo":"https://github.com/VectifyAI/PageIndex","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/pageindex","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"jupyter-mcp-server","name":"jupyter-mcp-server","author":"datalayer","domain":"data","integrations":["JupyterLab","Jupyter Notebook","VS Code","Claude","Cursor"],"language":null,"license":"BSD-3-Clause","stars":1227,"traits":["oss","mcp"],"summary":"MCP server giving AI agents full control over Jupyter notebooks — create cells, execute code, read outputs, and manage kernel state. Enables coding agents to run and inspect computational notebooks interactively.","repo":"https://github.com/datalayer/jupyter-mcp-server","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/jupyter-mcp-server","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}},{"slug":"unstract","name":"unstract","author":"Zipstack","domain":"data","integrations":["Claude","OpenAI","AWS Bedrock","Google Gemini","Qdrant","Pinecone","Snowflake","BigQuery","n8n"],"language":null,"license":"AGPL-3.0","stars":7083,"traits":["oss","mcp","keys"],"summary":"No-code LLM platform that turns unstructured documents (PDFs, images, scans) into structured JSON, exposing an MCP server agents can connect to for document extraction. Supports 9+ LLM providers, 5+ vector databases, and ETL connectors to S3, Snowflake, BigQuery, and more.","repo":"https://github.com/Zipstack/unstract","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/unstract","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}}]}