OpenBMB

    OpenBMB/UltraRAG

    #512 this week

    A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

    backend
    ai
    llm
    deepseek
    demo
    easy
    embedding
    flask
    Python
    Apache-2.0
    5.7K stars
    451 forks
    5.7K GitHub watchers
    Updated Oct 12, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    Ranks #512 of 2,845 repositories GStars tracks this week (top 18%).

    1 release in the last 90 days, the latest 27 days ago, with 21 contributors on GitHub.

    Peaked at #3 in the weekly ranking the week of Jan 18, its best in the past year.

    Use Cases & Benefits

    • Provides a low-code framework to build complex retrieval-augmented generation (RAG) pipelines using modular MCP architecture and YAML-based orchestration.
    • Enables rapid development and deployment of intricate RAG workflows with minimal coding by leveraging independent MCP servers and visual pipeline building.
    • Use for researchers to conduct reproducible RAG experiments with built-in evaluation, benchmark datasets, and detailed workflow analysis tools.
    • Use for developers to quickly prototype and deploy interactive conversational AI systems with one-click conversion from pipeline logic to web UI.
    • Use for industrial teams to integrate multimodal knowledge bases and large language models into scalable, customizable RAG applications with modular extensions.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present
    • Contributing guide: present
    • Code of conduct: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Less Code, Lower Barrier, Faster Deployment

    UltraRAG is the first lightweight RAG development framework based on the Model Context Protocol (MCP) architecture design, jointly launched by THUNLP at Tsinghua University, NEUIR at Northeastern University, OpenBMB, and AI9stars.

    Designed for research exploration and industrial prototyping, UltraRAG standardizes core RAG components (Retriever, Generation, etc.) as independent MCP Servers, combined with the powerful workflow orchestration capabilities of the MCP Client. Developers can achieve precise orchestration of complex control structures such as conditional branches and loops simply through YAML configuration.

    UltraRAG UI transcends the boundaries of traditional chat interfaces, evolving into a visual RAG Integrated Development Environment (IDE) that combines orchestration, debugging, and demonstration.

    Excerpt from the OpenBMB/UltraRAG README on GitHub (Apache-2.0 license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Forks

    451+17

    Open issues

    17-8

    Compared with peers in Backend

    Fastest-growing repositories GStars tracks in this cohort for the week of Oct 11, by 7-day star growth

    OpenBMB/UltraRAG compared with Backend repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    NationalSecurityAgency/ghidra93.2K+7.5K75today
    DuarteSantos8/openGym14.9K+4.4K5912 days ago
    K-Dense-AI/scientific-agent-skills53.9K+3.2K7521 days ago
    666ghj/MiroFish80.7K+2.4K23226 days ago
    anthropics/claude-plugins-official43.9K+2.3K35—
    OpenBMB/UltraRAG5.7K+07527 days ago
    Category median53.9K+3.2K59—

    Also by OpenBMB

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description