#104 · Primary category： Knowledge Base & RAG
EmbedAnything
Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀
Project last updated：08/12/26
GitHub Stars
1.3K
Forks
144
Contributors
22
License
Apache-2.0
Why we included this project
Teams building retrieval pipelines often hit a wall when embedding generation gets slow or expensive. EmbedAnything tackles that with a Rust core that produces dense, sparse, ONNX, and late-interaction embeddings from text, images, audio, PDFs, and web pages, then streams them into a vector database without holding the whole corpus in memory. The Python API keeps things approachable for data engineers and RAG developers, while the Rust library lets you embed inference directly into your own services. Since it runs locally via ONNX Runtime, you skip per-request API costs, which adds up when you're indexing millions of documents.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
docling
Get your documents ready for gen AI
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience