🧠UltraRAG
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
⭐ Popular: 6k stars, gaining about 6 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- Lets researchers and developers build RAG pipelines with conditional branches and loops in a few dozen lines of YAML instead of custom orchestration code.
- Serves an academic audience by making it easier to reproduce baselines, with the project referencing work tied to ICLR 2025 and ACL 2025.
- Ships a visual UI that turns a pipeline into an interactive web app and manages knowledge bases without separate front-end work.
under the hood
- Built on the Model Context Protocol, with RAG functions exposed as independent MCP servers orchestrated by an MCP client.
- Decomposes the pipeline into atomic servers such as retriever, reranker, generation, and embedding, with Milvus for vector storage.
- Primarily Python with a TypeScript and CSS UI, dependencies managed via uv, and both CPU and GPU Docker deployments.
Radar summary, generated from the project's public sources
star history
- PR#26 4k 2026-01-28
- now 6k + 1k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Better known than its recent output, coasting a little on attention.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Low-code MCP framework for complex RAG pipelines
similar projects
compare these →- 🖥️ Open WebUI
26× the stars
User-friendly AI Interface (Supports Ollama, OpenAI API,...)
149k ACTIVE - ⚡ Unsloth
13× the stars
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
72k ACTIVE - 🦙 LLaMA-Factory
13× the stars
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
74k ACTIVE
comments
Sign in with GitHub to add your blip on UltraRAG.