This is an early release preview. You may encounter bugs.

Research and write from your own sources

Deep-research pipelines, drafting tools and retrieval over your own documents.

29 tools · showing 1–24

Tool

LlamaIndex

MemoryData Wrangling

run-llama

Open-source data framework for building LLM and agentic apps over your own data, with 300+ integrations

ragvector-dbocr

A+
Tool

RAGFlow

Memory

infiniflow

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

ragdocument-processingknowledge-basecontext-engine

A+
Tool

Docling

Data Wrangling

docling-project

Parses PDFs and many other document formats into structured Markdown or JSON, with layout, table, formula, and OCR understanding

productivitydocument-processingocrragmarkdown

A+
Platform

OpenRAG

CodingMemory

langflow-ai

OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

ragdocument-processingsemantic-searchlangflow

A
Tool

OpenDataLoader PDF

Data Wrangling

opendataloader-project

Extract Markdown, JSON (with bounding boxes), and HTML from any PDF.

document-processingocraccessibilityrag

A
Tool

PaddleOCR

Data Wrangling

PaddlePaddle

OCR toolkit that converts PDFs and images into structured Markdown or JSON, with text, table, formula, and layout recognition

productivityocrdocument-processingtable-recognitionvision-language-model

A
Tool

PageIndex

MemoryResearch

VectifyAI

PageIndex: Document Index for Vectorless, Reasoning-based RAG.

ragvectorless-retrievaldocument-processingmcp-server

A
Platform

Superlinked Inference Engine (SIE)

InferenceDeploymentData Wrangling

superlinked

Self-hosted Kubernetes inference cluster serving LLMs, embeddings, rerankers, OCR and vision models with cluster-wide batching.

inference-serverkubernetesrerankingocr

A
Tool

ai.adeu/adeu

Data Wrangling

dealfluence

docxtrack-changesdocument-processingredline

A
Platform

Bisheng

Monitoring

dataelement

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI wo

ragorchestrationfine-tunedocument-processing

A
Tool

OfficeCLI

Data Wrangling

iOfficeAI

OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Fre

productivitydocxdocument-processingpowerpointcli

A
Tool

Skill_Seekers

Data Wrangling

yusufkaraaslan

The data layer for AI systems. Turns documentation sites, GitHub repos, PDFs, videos, notebooks, wikis, into structured knowledge assets, ready to power AI Skills, RAG pipelines, and AI coding assistants.

ragclaudegeminidocument-processing

A
Tool

MinerU

Data Wrangling

opendatalab

Converts PDFs and Office documents into LLM-ready Markdown and JSON with layout analysis, OCR and structure extraction

productivitydocument-processingocr

A
Tool

Zotero MCP

MemoryData Wrangling

cookjohn

It's a plugin extension in Zotero. Zotero MCP Plugin enables integration between AI assistants and Zotero through MCP. Zotero MCP Plugin 是一

zoterocitation-managementliterature-reviewsemantic-search

A
Tool

OpenKB

Data WranglingMemory

VectifyAI

VectifyAI’s OpenKB compiles raw documents into an interlinked Markdown knowledge base before agents query it. PDFs, docs

knowledge-baseragdocument-processingcli

A
Tool

PullMD

Data WranglingResearch

AeternaLabsHQ

Self-hosted URL- and file-to-Markdown service for humans and AI agents - web pages, documents, images, audio, YouTube. PWA + REST + MCP + Cl

html-to-markdownocryoutube-transcriptdocument-conversion

A
Tool

ContextGem

Data Wrangling

shcherbak-ai

Ask an LLM which clause a finding came from and it writes you a citation that reads right and points nowhere. ContextGem

document-processingstructured-outputcontract-analysis

B
Tool

Surya

Data Wrangling

datalab-to

OCR, layout analysis, reading order and table recognition in 90+ languages.

researchdocument-processingocr

B
Tool

LLM Graph Builder

MemoryData Wrangling

neo4j-labs

Turns unstructured documents, media, and web pages into a Neo4j knowledge graph using LLMs, with graph-aware chat over the result

knowledge-graphneo4jraglangchain

B
Tool

Doc7

Data Wrangling

magicrew

Turn documents into AI-ready Markdown with visual understanding

document-processingocrvision-language-modelmarkdown

B
Tool

Easy Dataset

Coding

ConardLi

Build LLM fine-tuning and evaluation datasets from documents with parsing, chunking, QA generation, and multi-format export

dataset-generationfine-tuneragevaluation

B
Tool

Hiring Agent

Data Wrangling

interviewstreet

Pipeline that scores resumes by extracting structured data from PDFs and enriching it with GitHub signals

recruitingproductivityresume-screeningdocument-processinggithub-signalsollama

B
Tool

Healthy Diet AI Agent

Memory

archie0732

Bun and TypeScript backend for nutrition chat, food-image analysis, and RAG document retrieval

raglangchainknowledge-graphnutrition

C
Tool

Document Structuring

Data WranglingMemoryCoding

barnetwang

Parses PDF and DOCX files by heading into Markdown chunks in a local SQLite FTS5 store for RAG retrieval

local-firstragsqlitehybrid-search

C

More ways in