“Ollama”

Use to launch, talk to, check, or clean up local Ollama models.

Post a messages to Ollama and send the result via mail

Queue manager skill for serializing local Ollama agent invocations from other skills; enqueues requests, runs one-at-a-time with queue.lock, writes callback…

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

Delegate edit/implementation work to a local LLM (Ollama-backed) running as a separate claude or opencode CLI process, while this session stays the…

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

Discover and probe publicly exposed Ollama (11434) and ComfyUI (8188) instances via Shodan, classify them, cache IPs over time, and optionally enrich with GPU…

Minion: manual-only routing note for using built-in subagents first, or direct Codex, Claude, Cursor, Grok, LM Studio, Ollama, and OpenRouter runners when…

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

使用自定义大模型（本地 Ollama 模型或远程 OpenAI 兼容 API，如 DeepSeek/OpenRouter）处理工作内容。当用户要求"用自定义大模型/自定义模型/本地模型/Ollama/DeepSeek/OpenRouter/qwen3…

Run prompts against a local LLM backend (LM Studio, Ollama, or MLX) with privacy-preserving output guardrails — drop reasoning_content, enforce structured…

Local-LLM fallback for cheap-operation routing — Ollama, llama.cpp, LM Studio.

Long-term memory via ChromaDB with local Ollama embeddings.

Seamless bidirectional bridge between nanobot (Ollama Mistral orchestrator) and overstory (Claude Code agent swarm).

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

Multi-step browser automation via browser-use — the open-source framework for autonomous browser navigation (91K+ stars, MIT).

Skill for searching and evolving the SQLite-backed Knowledge Graph.

Text embedding providers for semantic search and knowledge base indexing, supporting OpenAI, Voyage AI, Ollama, SiliconFlow, and Enconvo Cloud with…

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

Integrates local AI capabilities into applications using Embeddable Lemonade.

AI routing and token optimization tools for Dexter.

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

Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis.

Install the Context Index system — a progressive-disclosure mechanism that intercepts large tool outputs, saves them to disk, indexes them with a local small…