Maturity mature, very active: 8 tools compared (category, license, min RAM GPU)

8 of 40 rows from Local-AI Stack Directory: 40 Self-Hosted LLM & Vector-DB Tools, Verified Specs — every row carries the source it was checked against. Click a name for its notes.

tool name	category	license	min RAM GPU	offline capable	source URL
llama.cpp	LLM runtime	MIT	4GB+ RAM, CPU-only ok	yes	source
Ollama	LLM runtime	MIT	8GB RAM for 7B models	yes	source
vLLM	LLM runtime	Apache-2.0	16GB+ GPU VRAM recommended	yes	source
LangChain	RAG framework	MIT	depends on backend model	yes (with local models)	source
LlamaIndex	RAG framework	MIT	depends on backend model	yes (with local models)	source
Qdrant	Vector DB	Apache-2.0	2GB+ RAM, no GPU needed	yes	source
Milvus	Vector DB	Apache-2.0	8GB+ RAM recommended	yes	source
Elasticsearch	Search/vector DB	Elastic License 2.0/AGPL-3.0 dual	4GB+ RAM, scalable	yes	source

The full verified table: Local-AI Stack Directory: 40 Self-Hosted LLM & Vector-DB Tools, Verified Specs — 40 rows, CSV + JSON, every row with a checked source. €14 See the product

More slices of this table