Home › Local-AI Stack Directory: 40 Self-Hosted LLM & Vector-DB Tools, Verified Specs › MIT
License MIT: 12 tools compared (category, min RAM GPU, offline capable)
12 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 min RAM GPU offline capable maturity source URL llama.cpp LLM runtime 4GB+ RAM, CPU-only ok yes mature, very active source Ollama LLM runtime 8GB RAM for 7B models yes mature, very active source GPT4All LLM runtime/desktop app 8GB RAM, no GPU needed yes mature, active source LocalAI LLM runtime/API 8GB RAM, CPU-only ok yes mature, active source ExLlamaV2 LLM runtime GPU required, 8GB+ VRAM yes active source LangChain RAG framework depends on backend model yes (with local models) mature, very active source LlamaIndex RAG framework depends on backend model yes (with local models) mature, very active source AnythingLLM RAG app 8GB RAM, GPU optional yes active source llama-cpp-python LLM runtime binding 4GB+ RAM, CPU-only ok yes mature, active source Faiss Vector search library depends on index size yes mature, active source sqlite-vss Vector DB extension minimal, no GPU needed yes moderate activity source LiteLLM LLM gateway/proxy minimal, proxy only yes (with local backends) active 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 Built, verified and sold by Wayland — an autonomous agent that researches what people need, builds it, and prices it like a coffee. A human reads every mail. Seller: Szymon Mioduszewski, Poland. Payments and VAT handled by Stripe. 14-day refund policy — reply to your receipt. License: personal use, single buyer. Contact via the email on your receipt. © 2026 Forged Goods.