Alternatives and similar repositories for DeepSeek-OCR

Users that are interested in DeepSeek-OCR are comparing it to the libraries listed below

• ggsaddy / lab
  高级软件开发技术小组作业
  ☆24Updated last week
• microsoft / agent-lightning
  The absolute trainer to light up AI agents.
  ☆10,314Updated this week
• allenai / olmocr
  Toolkit for linearizing PDFs for LLM datasets/training
  ☆16,759Updated this week
• TencentCloudADP / youtu-agent
  A simple yet powerful agent framework that delivers with open-source models
  ☆4,248Updated this week
• HKUDS / RAG-Anything
  "RAG-Anything: All-in-One RAG Framework"
  ☆12,067Updated last week
• Alibaba-NLP / DeepResearch
  Tongyi Deep Research, the Leading Open-source Deep Research Agent
  ☆17,937Updated last week
• microsoft / magentic-ui
  A research prototype of a human-centered web agent
  ☆9,594Updated last month
• rednote-hilab / dots.ocr
  Multilingual Document Layout Parsing in a Single Vision-Language Model
  ☆6,120Updated 3 weeks ago
• shareAI-lab / learn-claude-code
  How can we build a true AI agent? Like Claude Code.
  ☆14,374Updated last week
• Tencent-Hunyuan / HunyuanOCR
  ☆1,445Updated this week
• zai-org / GLM-4.5
  GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
  ☆3,768Updated 3 weeks ago
• QwenLM / Qwen3-Omni
  Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, im…
  ☆3,280Updated last week
• MemTensor / MemOS
  Managing long-term, working, and external memory with OS-level scheduling, retrieval, and updates.
  ☆3,724Updated this week
• MoonshotAI / kimi-cli
  Kimi CLI is your next CLI agent.
  ☆3,858Updated this week
• zai-org / GLM-V
  GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
  ☆2,119Updated last month
• QwenLM / Qwen3-VL
  Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆17,808Updated 2 weeks ago
• bytedance / Dolphin
  The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
  ☆8,651Updated last month
• OpenPipe / ART
  Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…
  ☆8,139Updated last week
• Tencent / WeKnora
  LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
  ☆11,912Updated this week
• bytedance / trae-agent
  Trae Agent is an LLM-based agent for general purpose software engineering tasks.
  ☆10,545Updated 3 months ago
• microsoft / VibeVoice
  Open-Source Frontier Voice AI
  ☆20,325Updated last month
• MiroMindAI / MiroThinker
  MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 60.2% Avg@8 score on the challengi…
  ☆5,258Updated this week
• Yuliang-Liu / MonkeyOCR
  A lightweight LMM-based Document Parsing Model
  ☆6,437Updated last month
• MiniMax-AI / MiniMax-01
  The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention
  ☆3,298Updated 6 months ago
• OpenBMB / UltraRAG
  UltraRAG v2: A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
  ☆2,434Updated this week
• QwenLM / Qwen2.5-Omni
  Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and pe…
  ☆3,878Updated 7 months ago
• deepseek-ai / Engram
  Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
  ☆1,612Updated last week
• tadata-org / fastapi_mcp
  Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
  ☆11,367Updated last month
• MoonshotAI / Kimi-K2
  Kimi K2 is the large language model series developed by Moonshot AI team
  ☆9,818Updated 2 months ago
• HKUDS / DeepCode
  "DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
  ☆13,905Updated last week