Retrieval-Augmented Generation
Grounding model answers in retrieved documents. As of 2026-11-21, 1,193 indexed products match this subcategory (532 with full profiles); 394 were published in the last 90 days, against 277 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, Firecrawl leads, holding 6% of the stars of the 1,027 products here with their own repository. The most common form is MCP servers (79% of indexed products).
SubcategorySegment label: Crowded, slowing DER
Segment statistics
Whole catalogue (all 1,193 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 subcategory 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 0.022, attention is spread as if across about 46 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 | 945 | 79.2% | 291 |
| Infrastructure | 92 | 7.7% | 92 |
| Frameworks | 40 | 3.4% | 39 |
| Agent skills | 32 | 2.7% | 30 |
| Agent projects | 32 | 2.7% | 32 |
| Libraries | 22 | 1.8% | 21 |
| Plugins | 11 | 0.92% | 9 |
| AI APIs | 6 | 0.50% | 6 |
| SaaS products | 3 | 0.25% | 3 |
| IDE extensions | 3 | 0.25% | 3 |
| Automation platforms | 3 | 0.25% | 3 |
| Rules packs | 2 | 0.17% | 1 |
| Developer tools | 2 | 0.17% | 2 |
4 capabilities
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.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Semantic SearchSearching documents by meaning. | 409 | 178 | 103 | Crowded, slowing |
| Document IngestionParsing and chunking documents for retrieval. | 60 | 23 | 25 | Lagging the catalogue |
| RerankingReordering retrieved results by relevance. | 27 | 13 | 10 | Thin |
| Chat with DocumentsQuestion answering over a set of files. | 3 | 3 | 1 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled products only (532 of 1,193), 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 | 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 | ||
| 10 | ai-agents-for-beginners18 Lessons to Get Started Building AI Agents | Agent project | microsoft | 81k | 4d ago | MIT | ||
| 11 | 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 | ||
| 12 | 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 | ||
| 13 | 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 | ||
| 14 | 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 | ||
| 15 | DeepTutorDeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. | Agent project | HKUDS | 61k | 1d ago | Apache-2.0 | ||
| 16 | meilisearchA lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications. | Infrastructure | meilisearch | 60k | 1d ago | — | ||
| 17 | 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 | ||
| 18 | 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 | ||
| 19 | cherry-studioYour AI workspace for models, agents, and productivity. | Agent skill | CherryHQ | 54k | today | AGPL-3.0 | ||
| 20 | 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 | ||
| 21 | 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 | ||
| 22 | 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 | ||
| 23 | OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | Infrastructure | volcengine | 43k | today | AGPL-3.0 | ||
| 24 | 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 | ||
| 25 | 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 | ||
| 26 | PageIndex📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG | Agent project | VectifyAI | 41k | today | MIT | ||
| 27 | book-to-skillTurn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work. | Agent skill | virgiliojr94 | 39k | 2d ago | MIT | ||
| 28 | VaneVane is an AI-powered answering engine. | Agent project | ItzCrazyKns | 38k | 2mo ago | MIT | ||
| 29 | GraphRAGPipeline that extracts an entity knowledge graph and community summaries from text, enabling global and local graph-based retrieval. | Library | microsoft | 37k | 2d ago | MIT | ||
| 30 | QdrantVector search engine written in Rust with payload filtering, quantisation and hybrid sparse/dense search; self-hosted or Qdrant Cloud. | Infrastructure | qdrant | 36k | 1d ago | Apache-2.0 | ||
| 31 | CogneeMemory engine that turns documents and conversations into a knowledge graph plus vector index, exposed through add/cognify/search operations. | Library | topoteretes | 33k | 1d ago | Apache-2.0 | ||
| 32 | GraphitiPython library for building temporally aware knowledge graphs from episodes of data, with hybrid semantic, keyword and graph search for agent memory. | Library | Zep AI | 33k | 1d ago | Apache-2.0 | ||
| 33 | RAG_TechniquesThis repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial. | Infrastructure | NirDiamant | 30k | 19d ago | — | ||
| 34 | SimOpen-source visual canvas for building and deploying agent workflows, self-hosted or cloud. | Automation platform | Sim | 30k | today | Apache-2.0 | ||
| 35 | MastraTypeScript framework for agents, workflows, RAG, memory and evals, with a local dev playground and deploy targets for common hosts. | Framework | Mastra | 30k | today | Apache-2.0 | ||
| 36 | promptfooCLI and library for declarative prompt/model test suites, side-by-side comparisons and automated red-teaming of LLM apps and agents. | Developer tool | OpenAI (Promptfoo) | 28k | today | MIT | ||
| 37 | HaystackPython framework for composing pipelines and agents from components for retrieval, generation and tool use, aimed at production RAG and search. | Framework | deepset | 27k | today | Apache-2.0 | ||
| 38 | awesome-n8n-templates280+ free n8n automation templates — ready-to-use workflows for Gmail, Telegram, Slack, Discord, WhatsApp, Google Drive, Notion, OpenAI, and more. AI agents, RAG chatbots, email automation, social media, DevOps, and document processing. The largest open-source n8n template collection. | Agent project | enescingoz | 27k | 2mo ago | — | ||
| 39 | GenAI_Agents50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems. | Framework | NirDiamant | 25k | 19d ago | — | ||
| 40 | MaxKB🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 | MCP server | 1Panel-dev | 23k | today | GPL-3.0 |
Most common integrations
Third-party services named by products in this node, whole catalogue.
Launches per month
New Retrieval-Augmented Generation 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 | 4 |
| 2024-12 | 4 |
| 2025-01 | 3 |
| 2025-02 | 3 |
| 2025-03 | 5 |
| 2025-04 | 7 |
| 2025-05 | 8 |
| 2025-06 | 11 |
| 2025-07 | 5 |
| 2025-08 | 5 |
| 2025-09 | 18 |
| 2025-10 | 20 |
| 2025-11 | 11 |
| 2025-12 | 20 |
| 2026-01 | 21 |
| 2026-02 | 41 |
| 2026-03 | 53 |
| 2026-04 | 82 |
| 2026-05 | 72 |
| 2026-06 | 68 |
| 2026-07 | 126 |
| 2026-08 | 94 |
| 2026-09 | 92 |
| 2026-10 | 150 |
| 2026-11 | 126 |
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: RerankingReranking | High | Low | 60.0 |
| Coverage gap: Document IngestionDocument Ingestion | High | Low | 55.6 |
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 .