LaunchIndex
Category Discovery

Local AI & Runtime Tooling

Offline model runners, local inference GUIs, vector stores, and evaluation frameworks.

Pinned Category Spotlight (Top 3 Slots)

Spotlight tools receive priority positioning, social broadcast, and verified authority.

Claim Spotlight Slot ($49)
Local AI & Runtime Tooling
Weekly Winner
O

Ollama

Get up and running with large language models locally: Llama 3, Mistral, and Gemma

115000+3200/wkMITNative CLI / Docker / GPU accelerated
  • One-command model execution and local weight downloading
  • Drop-in OpenAI-compatible REST API endpoints (/v1/chat/completions)
  • Hardware GPU auto-detection for Apple Metal, NVIDIA CUDA, and AMD ROCm
Official WebsiteRead Review
Local AI & Run-Time Tooling
Weekly Winner
O

Open WebUI

User-friendly local AI interface supporting offline models with zero data telemetry

42500+2100/wkMITDocker-ready
  • Intuitive chat interface modeled after modern AI assistants
  • Direct Ollama and local LLM integration with automatic model pulling
  • Built-in RAG document question-answering with local vector embeddings
Official WebsiteRead Review

All Indexed Tools (2)

No additional tools indexed yet in this category.