“Ollama”

Use this skill when running, managing, or interacting with LLM models via `ollama` — locally or on a remote machine.

Use Ollama Cloud web APIs for single-query web search and single-page web fetch.

Stop Ollama model reload churn caused by callers sending different num_ctx values.

Install and configure Ollama for local embeddings with GrepAI.

Configure Ollama as embedding provider for GrepAI.

Complete Open WebUI API integration for managing LLM models, chat completions, Ollama proxy operations, file uploads, knowledge bases (RAG), image generation…

Set up and optimize a complete local AI infrastructure — Ollama, Open WebUI, local RAG pipelines, and private model serving.

Use when the user wants to test, compare, or choose local Ollama models for their machine.

Install, configure, and maintain Hermes Cortex — the observability and knowledge layer for Hermes Agent (Ollama, mycortex, Langfuse, Cortex Dashboard, nginx…

Install and configure Hermes Cortex core components — Ollama, mycortex knowledge brain, health server, agent registry, hooks, cron jobs, and profile…

Fetch URL → markdown / text / HTML via tokenhop /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents.

Running AI models locally with Ollama and llama.cpp.

Long-term memory via ChromaDB with local Ollama embeddings.

Connects NemoClaw to a local inference server.

Configure AI providers — Anthropic, OpenAI, a custom proxy/gateway (Azure or any OpenAI/Anthropic-compatible endpoint), or Ollama.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.

Organizes research with the self-hosted Open Notebook alternative to NotebookLM.

Integrates local AI capabilities into applications using Embeddable Lemonade.

Diagnoses why ROCm, the HIP SDK, PyTorch, or llama.cpp is broken on an AMD GPU on Linux, Windows, or WSL2, then applies a low-risk fix with consent or hands…

Automatically handles image editing, document conversion, audio/video editing, 3D rendering, diagrams, AI image generation, and more — using GIMP…

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.

llama.cpp local GGUF inference + HF Hub model discovery.

Set up, connect, validate, and repair Claude Desktop and MCP servers using Desktop Commander — inspecting and fixing mcp.json / claude_desktop_config.json…

Reference for the Claude API / Anthropic SDK - model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.