Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
docling-java
AI repositoriesA Java API for Docling
git clone https://github.com/docling-project/docling-java.git -
docling.rs
AI repositoriesFull Rust port of Python docling
git clone https://github.com/docling-project/docling.rs.git -
LightRAG
AI repositories[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
git clone https://github.com/HKUDS/LightRAG.git -
docling-Studio
AI repositoriesChunkless RAG for AI agents, powered by Docling. Parse your PDFs, inspect every title, table and box on the page, then let any MCP client (Claude, Cursor…) read only the sections it needs under a token budget and cite exact, server-verified passages. No chunks, no embeddings, no vector store.
git clone https://github.com/scub-france/docling-Studio.git -
haiku.rag
AI repositoriesAgentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
git clone https://github.com/ggozad/haiku.rag.git -
thesys-core
AI repositoriesOpen-source research workspace: search academic papers, upload PDFs, inline citations with on-PDF highlights, reader-mode Q&A, and get citation export in four formats.
git clone https://github.com/Sreehari05055/thesys-core.git -
chunky
AI repositoriesA local, open-source visual workspace for RAG document preparation: inspect PDF conversion, refine Markdown, compare chunking strategies, and enrich chunks before indexing.
git clone https://github.com/GiovanniPasq/chunky.git -
self-hosted-ai-stack
AI repositoriesDeploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP tools. Powered by Ollama, LiteLLM, AnythingLLM and more. Local-first with auto-configured authentication, lightweight stacks, optional HTTPS and NVIDIA GPU support. MIT licensed. Multi-arch: amd64, arm64.
git clone https://github.com/hwdsl2/self-hosted-ai-stack.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.