Data & Knowledge
Retrieval, databases, analytics, research and files that agents read and write. As of 2026-11-21, 7,219 indexed products match this ecosystem (1,971 with full profiles); 3,575 were published in the last 90 days, against 1,740 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, Firecrawl leads, holding 3% of the stars of the 5,051 products here with their own repository. The most common form is MCP servers (90% of indexed products).
EcosystemSegment label: Crowded, slowing DER
Segment statistics
Whole catalogue (all 7,219 indexed products, not only profiled ones). Calculated 2026-11-21.
Crowded, slowing. Among the largest fifth of nodes at its level, but its launches grew more slowly than the catalogue’s. Size is ranked against the other ecosystem nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.011, attention is spread as if across about 94 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 6,508 | 90.2% | 1,294 |
| Agent skills | 247 | 3.4% | 245 |
| Infrastructure | 149 | 2.1% | 148 |
| Plugins | 113 | 1.6% | 98 |
| Frameworks | 63 | 0.87% | 62 |
| Agent projects | 53 | 0.73% | 52 |
| Libraries | 29 | 0.40% | 27 |
| Rules packs | 21 | 0.29% | 9 |
| IDE extensions | 12 | 0.17% | 12 |
| AI APIs | 9 | 0.12% | 9 |
| SaaS products | 6 | 0.08% | 6 |
| Automation platforms | 4 | 0.06% | 4 |
| Platforms | 3 | 0.04% | 3 |
| Developer tools | 2 | 0.03% | 2 |
6 categories
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Category | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Public & Real-world DataMaps, weather, public datasets and other real-world information. | 2,011 | 188 | 1,113 | Crowded, slowing |
| Retrieval & RAGVector search, embeddings, RAG pipelines and knowledge graphs. | 1,756 | 751 | 598 | Crowded, slowing |
| Files & DocumentsReading, converting and processing files and documents. | 1,613 | 320 | 958 | Established |
| Research & KnowledgeAcademic research, deep research and knowledge bases. | 1,279 | 422 | 598 | Lagging the catalogue |
| DatabasesQuerying and managing SQL, NoSQL and hosted databases. | 805 | 355 | 383 | Lagging the catalogue |
| Data Engineering & AnalyticsWarehouses, pipelines and hands-on data analysis. | 606 | 325 | 271 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled products only (1,971 of 7,219), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | FirecrawlAPI that crawls and scrapes websites into clean Markdown or structured JSON, with search, map and agentic extract endpoints. | API | firecrawl | 206k | today | AGPL-3.0 | ||
| 2 | MarkItDownPython utility that converts PDF, Office, HTML, images and audio files into Markdown for LLM consumption. | Library | microsoft | 197k | 14d ago | MIT | ||
| 3 | DifyPlatform for building LLM apps and agent workflows visually with RAG pipelines, model management and app publishing. | Automation platform | LangGenius | 162k | today | LicenseRef-Dify-Open-Source-License | ||
| 4 | LangflowVisual builder for agent and RAG flows using drag-and-drop components, with flows deployable as APIs or MCP servers. | Automation platform | DataStax | 157k | today | MIT | ||
| 5 | graphifyTurn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store. | Agent project | Graphify-Labs | 151k | today | Apache-2.0 | ||
| 6 | LangChainFramework of model, tool, retriever and agent abstractions with hundreds of provider integrations; its agent API now runs on LangGraph. | Framework | LangChain | 150k | today | MIT | ||
| 7 | claude-memPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More | Agent skill | thedotmack | 119k | today | Apache-2.0 | ||
| 8 | RAGFlowSelf-hostable RAG engine with deep document parsing, template-based chunking, citations and an agent builder. | Framework | infiniflow | 94k | 1d ago | Apache-2.0 | ||
| 9 | Understand-AnythingGraphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more. | Agent skill | egonex.ai | 93k | 3d ago | MIT | ||
| 10 | MCP Reference ServersOfficial collection of reference MCP servers (filesystem, fetch, git, memory and others) demonstrating SDK usage. | Library | Agentic AI Foundation (Linux Foundation) | 92k | 2d ago | — | ||
| 11 | Crawl4AIOpen-source async web crawler that outputs LLM-ready Markdown and structured extraction, running headless browsers locally. | Library | unclecode | 88k | 1d ago | Apache-2.0 | ||
| 12 | MiroFishA Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物 | Infrastructure | 666ghj | 86k | 1mo ago | AGPL-3.0 | ||
| 13 | deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. | Agent project | bytedance | 86k | today | MIT | ||
| 14 | claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev. | MCP server | ruvnet | 82k | today | MIT | ||
| 15 | ai-agents-for-beginners18 Lessons to Get Started Building AI Agents | Agent project | microsoft | 81k | 4d ago | MIT | ||
| 16 | Prompt-Engineering-Guide🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. | Agent project | dair-ai | 80k | 8mo ago | MIT | ||
| 17 | DoclingDocument conversion toolkit that parses PDF, DOCX, PPTX, HTML and images with layout and table understanding into Markdown, JSON or DoclingDocument. | Library | IBM (LF AI & Data) | 71k | today | MIT | ||
| 18 | diagram-designEditorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop. | Agent skill | cathrynlavery | 70k | 2d ago | MIT | ||
| 19 | Mem0Memory layer that extracts, stores and retrieves long-term facts about users and sessions for agents, available as an open-source library or hosted platform. | Library | Mem0 | 69k | 3d ago | Apache-2.0 | ||
| 20 | anything-llmStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience | Agent project | Mintplex-Labs | 68k | today | MIT | ||
| 21 | TrendRadar⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, web search, MCP & smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅 + 定时联网搜索,支持关键词与 AI 智能筛选。AI 翻译 + AI 分析简报直推手机,支持接入 MCP 架构,赋能 AI 自然语言对话分析、实时检索、情感洞察与趋势预测。支持 Docker,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/Bark/Slack 等渠道智能推送。 | MCP server | sansan0 | 64k | today | GPL-3.0 | ||
| 22 | DeepTutorDeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. | Agent project | HKUDS | 61k | 1d ago | Apache-2.0 | ||
| 23 | meilisearchA lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications. | Infrastructure | meilisearch | 60k | 1d ago | — | ||
| 24 | ai-agent-book《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码 | Agent project | bojieli | 59k | 1mo ago | Apache-2.0 | ||
| 25 | servietteA no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway. | Infrastructure | pathwaycom | 59k | 11d ago | MIT | ||
| 26 | scientific-agent-skillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard. | Agent skill | K-Dense-AI | 58k | 5d ago | MIT | ||
| 27 | cherry-studioYour AI workspace for models, agents, and productivity. | Agent skill | CherryHQ | 54k | today | AGPL-3.0 | ||
| 28 | obsidian-skillsTeach your agent to use Obsidian and open formats including Markdown, Bases, JSON Canvas. | Agent skill | obsidianmd | 53k | 1d ago | MIT | ||
| 29 | LlamaIndexFramework for building agents and workflows over your data, with connectors, indexing, retrieval and an event-driven Workflows engine. | Framework | LlamaIndex | 53k | 1d ago | MIT | ||
| 30 | Codebase MemoryCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens. | MCP server | DeusData | 49k | today | MIT | ||
| 31 | MilvusDistributed vector database for billion-scale similarity search with many index types; Zilliz Cloud is the managed version. | Infrastructure | Zilliz (LF AI & Data) | 47k | today | Apache-2.0 | ||
| 32 | LangGraphLow-level orchestration framework that models agents as stateful graphs with checkpointing, human-in-the-loop interrupts and durable execution. | Framework | LangChain | 45k | today | MIT | ||
| 33 | mcp-serverPuter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more | MCP server | puter.com | 44k | today | AGPL-3.0 | ||
| 34 | openhumanThe fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS. | Agent project | tinyhumansai | 43k | 1d ago | GPL-3.0 | ||
| 35 | BettaFish微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。 | Framework | 666ghj | 43k | 1mo ago | GPL-2.0 | ||
| 36 | OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | Infrastructure | volcengine | 43k | today | AGPL-3.0 | ||
| 37 | FaissC++/Python library for efficient similarity search and clustering of dense vectors, including GPU index implementations. | Library | Meta | 42k | 1d ago | MIT | ||
| 38 | MarkerConverts PDFs, images and Office documents to Markdown, JSON or HTML using deep-learning OCR and layout models, with optional LLM refinement. | Library | Datalab | 41k | 1d ago | Apache-2.0 | ||
| 39 | LightRAGGraph-enhanced RAG system that indexes entities and relations alongside vectors for dual-level retrieval, with a server and web UI. | Library | HKU Data Intelligence Lab | 41k | today | MIT | ||
| 40 | tidbTiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling. | Infrastructure | pingcap | 41k | today | Apache-2.0 |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| PostgreSQL | 286 | 4.0% |
| MySQL | 112 | 1.6% |
| Google Maps | 109 | 1.5% |
| Obsidian | 109 | 1.5% |
| GitHub | 60 | 0.8% |
| Redis | 60 | 0.8% |
| Microsoft Excel | 59 | 0.8% |
| YouTube | 50 | 0.7% |
| Supabase | 47 | 0.7% |
| Google Sheets | 46 | 0.6% |
| Google Drive | 34 | 0.5% |
| MongoDB | 29 | 0.4% |
| Apache Kafka | 27 | 0.4% |
| BigQuery | 27 | 0.4% |
| Snowflake | 26 | 0.4% |
Launches per month
New Data & Knowledge products per monthSRC
Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-11 | 6 |
| 2024-12 | 10 |
| 2025-01 | 3 |
| 2025-02 | 7 |
| 2025-03 | 18 |
| 2025-04 | 19 |
| 2025-05 | 14 |
| 2025-06 | 16 |
| 2025-07 | 9 |
| 2025-08 | 11 |
| 2025-09 | 88 |
| 2025-10 | 68 |
| 2025-11 | 40 |
| 2025-12 | 63 |
| 2026-01 | 71 |
| 2026-02 | 172 |
| 2026-03 | 245 |
| 2026-04 | 357 |
| 2026-05 | 332 |
| 2026-06 | 641 |
| 2026-07 | 609 |
| 2026-08 | 603 |
| 2026-09 | 896 |
| 2026-10 | 1,418 |
| 2026-11 | 1,074 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
| Opportunity | Competition | Confidence | Score |
|---|---|---|---|
| Coverage gap: Chat with DocumentsChat with Documents | Low | Low | 64.0 |
| Coverage gap: NotebooksNotebooks | High | Low | 61.7 |
| Coverage gap: Entity ExtractionEntity Extraction | Medium | Low | 60.2 |
| Coverage gap: RerankingReranking | High | Low | 60.0 |
| Coverage gap: Schema InspectionSchema Inspection | High | Low | 58.6 |
| Coverage gap: Database MigrationsDatabase Migrations | High | Low | 58.2 |
| Coverage gap: Multimodal EmbeddingsMultimodal Embeddings | Low | Low | 58.0 |
| Coverage gap: Query OptimizationQuery Optimization | High | Low | 57.6 |
| Coverage gap: Text EmbeddingsText Embeddings | Medium | Low | 57.4 |
| Coverage gap: SQL QueryingSQL Querying | High | Low | 57.0 |
| Coverage gap: Data VisualizationData Visualization | High | Low | 56.7 |
| Coverage gap: Document IngestionDocument Ingestion | High | Low | 55.6 |
| Coverage gap: Local File AccessLocal File Access | High | Low | 55.2 |
| Coverage gap: Team WikisTeam Wikis | High | Low | 54.3 |
| Coverage gap: Fact-checkingFact-checking | High | Low | 54.2 |
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .