#
Starred repositories
122
results
for source starred repositories
written in Python
Clear filter
Get your documents ready for gen AI
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
Federated query engine for AI - The only MCP Server you'll ever need
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous …
Convert PDF to markdown + JSON quickly with high accuracy
An open-source RAG-based tool for chatting with your documents.
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations.
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
OCR, layout analysis, reading order, table recognition in 90+ languages
Open Source AI Platform - AI Chat with advanced features that works with every LLM
Beta release of Archon OS - the knowledge and task management backbone for AI coding assistants.
Open Source Alternative to NotebookLM / Perplexity, connected to external sources such as Search Engines, Slack, Linear, Jira, ClickUp, Confluence, Notion, YouTube, GitHub, Discord and more. Join o…
"RAG-Anything: All-in-One RAG Framework"
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
High accuracy RAG for answering questions from scientific documents with citations
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
Multilingual Document Layout Parsing in a Single Vision-Language Model
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
A Unified Toolkit for Deep Learning Based Document Image Analysis
The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework. Website: https://swarms.ai
📄 Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVINO, PaddlePaddle and PyTorch.
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas