AgentSidekick

Document Ingestion

Parsing and chunking documents for retrieval. As of 2026-11-21, 60 indexed products offer it (23 with full profiles), in 5 forms: 47 MCP servers, 6 Agent skills, 4 Libraries, 2 AI APIs. 25 were published in the last 90 days, against 10 in the 90 days before. RAGFlow has the most GitHub stars, 36% of the total across 46 products with their own repository.

CapabilitySegment label: Lagging the catalogue DERScored as an opportunity

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 47 indexed · 10 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

Document Ingestion: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1Docling MCPConvert PDFs and other documents to structured formats via Docling, for AI applications.docling-project8027d ago
2haiku.ragLocal-first agentic RAG with citations - hybrid search, reranking, multimodal document retrievalggozad6651d ago
3pagesiftLocal-first web & document ingestion engine in Rust — HTTP/browser capture, layout-aware PDF/Office/OCR parsing, persistent sync, verifiable data graphs, and evidence-grounded AI context.YOLOW922933d ago
4flexible-graphragGraphRAG, RAG, LlamaIndex, LangChain, 15 Prop Graph, 4 RDF, 10 Vector, 3 Search DBs. 14 data srcs, auto sync, Alfresco, Nuxeo, SharePoint, Box, CMIS, S3,GCS,Azure, web. KG auto-bld, Ontologies, 13 LLM providers, Docling, LlamaParse, LiteParse, Hybrid Search, AI Chat. TypeScript React, Vue, Angular, Python, REST, MCP, OpenArch, Langflow, CocoIndex.stevereiner204today
5docling.rsDocuments to Markdown for agents: PDF layout, tables and OCR, Office, HTML, scans. docling in Rust.docling-project142today
6pdfmuxPDF-to-Markdown extraction that audits its own output and flags any extractor's silent drops.NameetP871d ago
7DocSlicerAnswer questions from documents too large to fit in context, reading only the sections you need.DocSlicer362mo ago
8Local FAISS MCP ServerLocal FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.nonatofabio367mo ago
9WebSearch MCP ServerZero-API-key MCP search server: multi-engine web/academic search, PDF parsing, secure web fetchdaidaiJ30today
10truecopyRead tables, figures and dates out of a PDF, Word file, CSV or paste, with a verdict on the reading.truecopydev31d ago

Agent skills 6 indexed · 6 profiled

Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms

Document Ingestion: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1carrelOntology-Augmented Generation for AI agents. FengZhenfei8084d ago
2daskScales pandas, NumPy, and custom Python research workflows beyond memory or across clusters with Dask. Covers DataFrames, Arrays, Bags, Futures, chunking, schedulers, and distributed diagnostics. Use for partitioned file processing, scientific array computation, or parallel tasks whose memory and dependency structure require Dask.K-Dense-AI—5d ago
3rag-engineerExpert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.sickn33—1d ago
4rag-implementationRAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.sickn33—1d ago
5agent-memory-systemsMemory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragmdavila7—today
6agents-llamaindexData framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.davila7—today

Libraries 4 indexed · 4 profiled

No compatibility evidence is collected for this form.

Document Ingestion: Libraries by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1DoclingDocument conversion toolkit that parses PDF, DOCX, PPTX, HTML and images with layout and table understanding into Markdown, JSON or DoclingDocument.IBM (LF AI & Data)71ktoday
2MarkerConverts PDFs, images and Office documents to Markdown, JSON or HTML using deep-learning OCR and layout models, with optional LLM refinement.Datalab41k1d ago
3LightRAGGraph-enhanced RAG system that indexes entities and relations alongside vectors for dual-level retrieval, with a server and web UI.HKU Data Intelligence Lab41ktoday
4UnstructuredLibrary and hosted platform for partitioning PDFs, Office files, HTML and images into structured elements and chunks for RAG pipelines.Unstructured16k1d ago

AI APIs 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Document Ingestion: AI APIs by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1LlamaParseHosted document parsing API that uses vision and language models to convert complex PDFs, slides and spreadsheets into Markdown or JSON.LlamaIndex681d ago
2ReductoDocument ingestion API that parses, splits and extracts structured data from complex PDFs and spreadsheets using vision models.Reducto——

Frameworks 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Document Ingestion: Frameworks by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1RAGFlowSelf-hostable RAG engine with deep document parsing, template-based chunking, citations and an agent builder.infiniflow94k1d ago

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
Azure11.7%
OneDrive / SharePoint11.7%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
document ingestion4
document parsing13
pdf parsing5
chunking19
unstructured.io0
docling18
llamaparse1

Segment statistics

Whole catalogue (60 indexed products). Calculated 2026-11-21.

60DERIndexed products23 with full profiles
25DERLaunched, last 90 days10 in the 90 days before
36DERMomentum vs catalogue50 = same pace as the catalogue
36%DERLargest project's share of starsAcross 46 products with their own repository
0.248DERConcentration (HHI)About 4 equal-sized projects’ worth; moderately concentrated
2SRCMedian starsPer product with its own repository
83%DEROpen sourceMarked open source; unknown counts as not

Lagging the catalogue. Mid-sized among capabilities, with launches growing more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.248 means stars are spread as if across about 4 equally popular projects — moderately concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Scored as an opportunity

Score breakdown

Coverage gap: Document Ingestion: score 55.6 HEU, competition High, confidence Low. Only 60 indexed products match "Document Ingestion", against 1193 in Retrieval-Augmented Generation overall.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .