Ollama is an open-source project that allows you to run large language models (LLMs) locally on your own hardware, providing a way to use AI capabilities privately without sending data to external services.
Why this server?
Leverages local Ollama LLM for offline diagnosis and remediation, avoiding external API calls.
Why this server?
Allows using local Ollama models as workers in MergeLoop, enabling on-device inference alongside other workers.
Why this server?
Provides a gateway to route and load-balance requests across multiple Ollama instances, with session affinity and latency-based routing.
Why this server?
Integrates with Ollama for local AI-powered natural language to SQL query generation.
Why this server?
Uses Ollama as an embeddings backend to enable semantic and graph-seeded retrieval across vault notes.
Why this server?
Allows managing local Ollama models: discover installed and loaded models, pull/remove models, load/unload from memory, check hardware fit, and offload inference (completion and embedding) to local Ollama instances.
Why this server?
Allows querying local Ollama models via HTTP.
Why this server?
Provides a preset tunnel configuration for Ollama with authentication enabled on port 11434, enabling secure external access to local Ollama instances.
Why this server?
Provides tools for predicting LLM performance and optimizing local LLM inference using Ollama, including checking compatibility of specific models and getting recommendations.
