# superlinked/sie

Open-source inference server and production cluster for all the models your agent needs.

Repository: https://github.com/superlinked/sie
Canonical: https://ross.abutalabs.com/products/sie
Homepage: https://superlinked.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: embeddings, vector-search, data-pipeline, deep-learning, information-retrieval, llm, ml, mlops, natural-language-processing, nlp, python, retrieval, retrieval-augmented-generation, semantic-search, inference, bge, colbert, inference-server, reranking, splade
Last push: 2026-08-21T20:28:04+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 96, longevity 73
- inputs: {"age_days": 1030, "days_push": 12, "days_rel": 24, "gap_med": 1, "n_releases_24m": 46}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2830, forks 280 (observed 2026-08-28T04:07:24.326559+00:00)

## What it is
SIE (Superlinked Inference Engine) is an open-source, self-hosted inference server and production cluster that serves 100+ open models (embedders, rerankers, extractors, LLMs) behind one OpenAI-compatible API. It handles multi-model GPU sharing, on-demand model loading, and ships a full production stack with KEDA autoscaling and Terraform for GKE, EKS, and AKS.

## Use cases
- self-host embeddings and rerankers for RAG
- run open LLM inference in my own cloud
- replace per-token embedding API costs with self-hosted models
- serve many small ML models on one GPU
- add semantic search embeddings to Qdrant or Weaviate
- deploy an OpenAI-compatible inference endpoint on Kubernetes
- extract entities and OCR documents for agent pipelines
- air-gapped inference for agents

## When to choose
- You need self-hosted, privacy-preserving inference for embeddings, reranking, extraction, and small LLMs behind one API
- You run many small models on shared GPUs and need fast model switching
- You want OpenAI-compatible endpoints for drop-in migration from hosted APIs
- You need production deployment with autoscaling on GKE, EKS, or AKS

## When to avoid
- You only need to serve one very large model across many GPUs - tools like vLLM or SGLang alone fit better
- You want a fully managed hosted API with no infrastructure to run
- You need non-Python/TypeScript SDKs or integrations beyond the supported vector stores and agent frameworks

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, rag, machine-learning, nlp, search-engine, ocr, api-framework, http-server, gpu-computing, sdk
- domain: machine-learning, large-language-models, self-hosted, developer-tools
- platform: python, self-hosted, cloud, cross-platform
- tags: inference-server, embeddings, reranking, vector-search, openai-compatible-api, model-serving, rag-pipeline, gpu-sharing, semantic-search, splade, colbert, mlops, retrieval-augmented-generation, natural-language-processing, search, ai-agents, docker, kubernetes, gpu, linux, macos

## Member repositories
- superlinked/sie (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:24.326559+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 2026-08-30T07:38:10.835941+00:00, confidence not recorded.
  - readme: https://github.com/superlinked/sie (fetched 2026-08-28T04:07:24.326559+00:00, sha e4a4011b2872)
  - homepage: https://superlinked.com (fetched 2026-08-29T09:53:33.544776+00:00, sha 3526d02626b4)
  - site_page: https://superlinked.com/docs/examples (fetched 2026-08-29T09:53:33.547503+00:00, sha 9c55e0c185c2)
  - site_page: https://superlinked.com/docs (fetched 2026-08-29T09:53:33.549669+00:00, sha 9d6306f6630a)
  - site_page: https://superlinked.com/docs/integrations/chroma (fetched 2026-08-29T09:53:33.551926+00:00, sha ef8d5ea10658)
  - site_page: https://superlinked.com/docs/integrations/lancedb (fetched 2026-08-29T09:53:33.554153+00:00, sha 9a7bc0ad6ee7)
  - site_page: https://superlinked.com/docs/integrations/qdrant (fetched 2026-08-29T09:53:33.556855+00:00, sha ad712eace48a)
  - site_page: https://superlinked.com/docs/integrations/weaviate (fetched 2026-08-29T09:53:33.559294+00:00, sha b368fdba0731)
  - site_page: https://superlinked.com/docs/deployment (fetched 2026-08-29T09:53:33.561700+00:00, sha 0c259de0a596)
  - site_page: https://superlinked.com/docs/deployment/cloud-aws (fetched 2026-08-29T09:53:33.564136+00:00, sha f74823ceebea)
- Data as of 2026-08-30T08:39:29.467469+00:00.