First question
What should AI find?
Document tools differ by ingestion, indexing, retrieval, citations, and how much of the source material they bring into context.
Theme
AI Resources
Use AI with documents and knowledge bases
A focused map for retrieval, RAG, document context, knowledge-base, and indexing tools that help AI work with files and source material.
Use this page to narrow what to explore next, then open the original source before relying on setup, privacy, citations, scale, or cost assumptions.
Questions to check
Start with the job or constraint that matters now.
These checks frame the source-linked Resources below. They do not rank products or cover every option.
Data path
Check where files go
Look at what data is indexed, where it is stored, which model providers are involved, and who can access the knowledge base.
Trust habit
Keep the source trail visible
A useful document workflow should make it easier to return to the original file, citation, note, or record when an answer matters.
Coverage and freshness
Newest LifeHubber addition included here: July 7, 2026
These groups are selective starting points, not a complete directory. The date reflects the newest included Resource’s LifeHubber added date, not a recheck of every linked source. Check the original source for current setup, terms, limits, privacy, access, costs, and behaviour.
Fresh in this topic
Newer Resources already included in this map
1Recently added Resources from the groups below.
Documents and knowledge bases
Projects that bring source material into context
11Use this group when the job is searching documents, indexing files, building a knowledge base, or giving an agent source material it can retrieve.
RAGFlow
infiniflow/ragflow
Why it fits this starting point
Document ingestion, chunking, retrieval, citations, and knowledge workflows cover the full RAG pipeline rather than only vector storage.
PageIndex
VectifyAI/PageIndex
Why it fits this starting point
A vectorless tree index with traceable reasoning-based retrieval puts document structure and explainable search paths ahead of embedding similarity.
Dify
langgenius/dify
Why it fits this starting point
Visual RAG pipelines connect knowledge retrieval, agent tools, model providers, and application flows in one configurable workflow layer.
Onyx
onyx-dot-app/onyx
Why it fits this starting point
A self-hostable interface combines RAG with web search, code execution, file creation, and deep research when retrieval must sit inside a broader workbench.
Vane
ItzCrazyKns/Vane
Why it fits this starting point
Cited search-style answers, file uploads, SearxNG web search, and a Docker route bring private documents and web results into one answering workflow.
LLM Wiki
nashsu/llm_wiki
Why it fits this starting point
Document-to-wiki conversion, source traceability, graph search, and a desktop app show a maintained-knowledge-page route beyond question-by-question retrieval.
CodeGraph
colbymchenry/codegraph
Why it fits this starting point
Symbol relationships, call graphs, framework-aware routes, and auto-sync give coding agents structural codebase context instead of plain text chunks.
Understand Anything
Lum1104/Understand-Anything
Why it fits this starting point
A knowledge graph, diff-impact views, tours, and plugins across coding environments show code understanding shared across tools and workflows.
LEANN
yichuan-w/LEANN
Why it fits this starting point
A local vector database with a lower-storage design puts index size and local operation ahead of application features in the comparison.
CocoIndex
cocoindex-io/cocoindex
Why it fits this starting point
Delta-only processing, lineage, and multiple index targets keep knowledge pipelines current without rebuilding unchanged data.
MaxKB
1Panel-dev/MaxKB
Why it fits this starting point
Document and web collection, hybrid retrieval, embedded Q&A, and offline Docker paths span knowledge ingestion, retrieval method, and delivery inside another site.
Also in AI
Follow the next layer.
Keep the thread going with AI Guides for decision habits for messy AI choices, AI Access for free and low-cost ways to compare AI model access, AI Ballot for a clearer view of what readers are leaning toward.