Agent infrastructure
sie
superlinked/sie
A self-hosted inference server and production cluster that serves 100+ open models behind one OpenAI-compatible API, covering embeddings, reranking, OCR, classification, and generation for agent workloads.
Topics
Related projects
unstructured15.7kAn open-source ETL library that partitions PDFs and other documents into clean, structured chunks ready for LLMs and RAG pipelines.
FlagEmbedding12.3kA one-stop retrieval toolkit around BGE embedding and reranker models, with inference, fine-tuning, evaluation, and RAG support.
deeplake9.3kAn AI database and multimodal data lake serving as serverless vector store for retrieval and training.
prompttools3.1kAn open-source Python library for testing prompts across LLMs and vector databases with notebooks and playground.
web-llm19.4kA high-performance in-browser LLM inference engine with WebGPU acceleration and OpenAI-compatible APIs for building private web AI apps.
nano-vllm16.3kA lightweight vLLM reimplementation in about 1,200 lines of Python delivering fast, readable offline LLM inference.