Alternatives and similar repositories for qwen2.5VLM-OCR

Users that are interested in qwen2.5VLM-OCR are comparing it to the libraries listed below

• ikantkode / exaOCR
  A simple CPU only OCR for pdf/images/word/excel to markdown. With streamlit.
  ☆20Updated 3 weeks ago
• AKSarav / pdfstract
  PDF to MD UI - User Interface to Convert PDF to MarkDown for LLM and RAG
  ☆44Updated 2 weeks ago
• ganeshnikhil / Kgraph
  generate informative knowledge graph from text using open source models , ollama
  ☆22Updated 3 weeks ago
• mpaepper / vibevoice
  Fast local speech-to-text for any app using faster-whisper
  ☆113Updated this week
• GVDub / panai-seed-node
  “A locally hosted, memory-aware AI microservice—designed for cultural continuity, decentralized intelligence, and ethical autonomy.”
  ☆28Updated 4 months ago
• hyepartners-gmail / vibevideo-mcp
  Agent MCP for ffmpeg
  ☆203Updated 3 months ago
• prateekvellala / retrieval-experiments
  Exploring retrieval systems for language models
  ☆14Updated 5 months ago
• hydropix / TranslateBookWithLLM
  A python script designed to translate large amounts of text with an LLM and the Ollama API
  ☆121Updated this week
• tarun7r / Vocal-Agent
  Cascading voice assistant combining real-time speech recognition, AI reasoning, and neural text-to-speech capabilities.
  ☆118Updated 2 weeks ago
• lynthera / bitsegments_localminds
  Offline LLM chatbot with personalized memory — works on CPU with multi-session memory support.
  ☆22Updated 3 months ago
• yamalight / litlytics
  🔥 LitLytics - an affordable, simple analytics platform that leverages LLMs to automate data analysis
  ☆101Updated 9 months ago
• ikantkode / pdfLLM
  pdfLLM is a completely open source, proof of concept RAG app.
  ☆152Updated 3 weeks ago
• Buddie-AI / Buddie
  BUDDIE is the first full-stack open-source AI voice interaction solution, providing a complete end-to-end system from hardware design to …
  ☆152Updated last month
• MehulG / memX
  A real-time shared memory layer for multi-agent LLM systems.
  ☆48Updated 2 months ago
• adspiceprospice / localOCR
  Using Gemma-3 Vision
  ☆106Updated 5 months ago
• Pavankunchala / LLM-Learn-PK
  Testing the different LLM and RAG Tests while I learn along the way
  ☆204Updated 3 months ago
• Ablasko32 / Project-Shard
  Make AI Free Again - Shard is a GUI for Ollama LLM's. Powered by Next.js.
  ☆60Updated 6 months ago
• mixtcha / mixtcha
  quickly mix LLMs together
  ☆18Updated 8 months ago
• guerra2fernando / libriscribe
  Libriscribe is an AI-powered open-source book creation system. The system is designed to help you write your book, from initial concept …
  ☆38Updated 6 months ago
• CalvesGEH / VoiceCraftAPI
  An API for VoiceCraft.
  ☆25Updated last year
• Forest-Person / smolResearcher
  Use smol agents to do research and then update csv coumns with its findings.
  ☆41Updated 7 months ago
• misbahsy / Scenic-Flow
  A Simple Scenes Based Movie Generation App
  ☆51Updated 10 months ago
• anishgowda21 / tiny-ollama-chat
  A lightweight UI for chatting with Ollama models. Streaming responses, conversation history, and multi-model support.
  ☆120Updated 6 months ago
• Dcup-dev / dcup
  The Ultimate Open-Source RAG-as-a-Service Platform ☕
  ☆48Updated 3 months ago
• HafizalJohari / lclv
  ☆90Updated 3 months ago
• moaljumaa / halfwayml_open
  Open source tool for transcirption and subtitling, alternative to happyscribe.
  ☆30Updated 7 months ago
• enescingoz / colab-llm
  This repository provides a ready-to-use Google Colab notebook that turns Colab into a temporary server for running local LLM models using…
  ☆75Updated 5 months ago
• bloodworks-io / phlox
  Self-hosted AI medical scribe.
  ☆50Updated last week
• navedmerchant / MyDeviceAI
  A cross patform app that unlocks your devices Gen AI capabilities
  ☆63Updated last week
• aalapd / wormpy
  A simple Python-based tool designed to scrape websites for content.
  ☆57Updated 11 months ago