Hi — I curate StackMap, a hand-curated knowledge graph of open-source AI/agent tools. Every entry is human-reviewed: a summary, an opinionated note on when to use it (and when not), and typed edges to what it pairs with or competes against — with the why written down.
sie earned a place on the map:
How we mapped it:
- alternative to
vllm — Both self-hosted OpenAI-compatible inference servers, opposite shapes: vLLM maximizes throughput for one big LLM; SIE serves breadth — 100+ heterogeneous task models (embedders, rerankers, OCR, NER, guards) loaded on demand across a cluster.
- alternative to
ollama — Same 'serve open models behind one local API' job at different scales: Ollama is the single-machine developer runner; SIE is the multi-model production cluster with autoscaling, gateway and Terraform.
- built with
mineru — MinerU ships in SIE's model catalog as a backend for the document-to-markdown task — SIE serves it (alongside GLM-OCR, PaddleOCR-VL and docling) behind its unified API.
If any of this misrepresents the project — an edge you'd dispute, a sharper "when NOT to use" — reply here and a human fixes it. And feel free to just close this issue; it's only a heads-up.
Hi — I curate StackMap, a hand-curated knowledge graph of open-source AI/agent tools. Every entry is human-reviewed: a summary, an opinionated note on when to use it (and when not), and typed edges to what it pairs with or competes against — with the why written down.
sie earned a place on the map:
How we mapped it:
vllm— Both self-hosted OpenAI-compatible inference servers, opposite shapes: vLLM maximizes throughput for one big LLM; SIE serves breadth — 100+ heterogeneous task models (embedders, rerankers, OCR, NER, guards) loaded on demand across a cluster.ollama— Same 'serve open models behind one local API' job at different scales: Ollama is the single-machine developer runner; SIE is the multi-model production cluster with autoscaling, gateway and Terraform.mineru— MinerU ships in SIE's model catalog as a backend for the document-to-markdown task — SIE serves it (alongside GLM-OCR, PaddleOCR-VL and docling) behind its unified API.If any of this misrepresents the project — an edge you'd dispute, a sharper "when NOT to use" — reply here and a human fixes it. And feel free to just close this issue; it's only a heads-up.