# StarlightSearch/EmbedAnything

Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

Repository: https://github.com/StarlightSearch/EmbedAnything
Canonical: https://ross.abutalabs.com/products/embedanything
Homepage: https://embed-anything.com/
Language: Rust
License: Apache-2.0
License Family: permissive
Topics: machine-learning, indexing, rag, rust, information-retrieval, vector-database, high-performance, inference, python, onnxruntime, server, cloud, ai, pipeline, search, large-language-models, production-ready, hacktoberfest, generative-ai, local
Last push: 2026-08-12T08:56:59+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 92, longevity 63
- inputs: {"age_days": 885, "days_push": 21, "days_rel": 54, "gap_med": 6, "n_releases_24m": 30}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1305, forks 143 (observed 2026-08-28T04:04:18.730896+00:00)

## What it is
EmbedAnything is a high-performance, memory-safe embedding pipeline written in Rust (with Python bindings) that generates embeddings from text, PDFs, images, audio, video, and webpages. It streams vectors efficiently to any vector database and supports dense, sparse, ONNX, model2vec, and late-interaction embedding models, including cloud providers.

## Use cases
- generate embeddings for pdfs and documents
- build a rag pipeline with a vector database
- embed images and audio files locally
- index a directory of files into a vector store
- run embedding inference without pytorch
- chunk and embed webpages for search
- use colbert or colpali late-interaction embeddings

## When to choose
- you need fast, low-memory, production-ready embedding ingestion in Rust or Python
- you want multimodal embedding (text, images, audio, video, pdfs) in one pipeline
- you want to avoid a PyTorch dependency for deployment
- you need streaming indexing into multiple vector databases with minimal code

## When to avoid
- you need to train or fine-tune embedding models
- you only need a hosted embedding API with no local pipeline
- your stack is pure Python and you prefer native PyTorch tooling like sentence-transformers

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-inference, rag, vector-database, search-engine, ocr, audio-processing, video-processing, pdf, etl
- domain: machine-learning, large-language-models, developer-tools
- platform: rust, python, cross-platform, cloud, self-hosted
- tags: embeddings, multimodal, onnx, candle, vector-streaming, chunking, late-interaction, colpali, colbert, reranker, whisper, information-retrieval, retrieval-augmented-generation, search, natural-language-processing, gpu

## Member repositories
- StarlightSearch/EmbedAnything (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:18.730896+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:51:00.723842+00:00, confidence not recorded.
  - readme: https://github.com/StarlightSearch/EmbedAnything (fetched 2026-08-28T04:04:18.730896+00:00, sha cbc49625383d)
  - homepage: https://embed-anything.com/ (fetched 2026-08-29T12:08:50.728062+00:00, sha 72a57efd3f96)
  - site_page: https://embed-anything.com/references (fetched 2026-08-29T12:08:50.731004+00:00, sha 6cb5722cb60a)
- Data as of 2026-08-30T08:39:29.467469+00:00.