菜单
Start and verify the local Ollama LLM server. Use when Ollama is needed for RLM distillation, seal snapshots, embeddings, or any local LLM inference — and it's not already running. Checks if Ollama is running, starts it if not, and verifies the health endpoint.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/richfrem/Project_Sanctuary --skill ollama-launch命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | ollama-launch |
| description | Start and verify the local Ollama LLM server. Use when Ollama is needed for RLM distillation, seal snapshots, embeddings, or any local LLM inference — and it's not already running. Checks if Ollama is running, starts it if not, and verifies the health endpoint. |
Ollama provides local LLM inference for RLM distillation (seal phase summarization) and embeddings.
Connection refused to 127.0.0.1:11434[DISTILLATION FAILED] for new files# Check if Ollama is already running
curl -sf http://127.0.0.1:11434/api/tags > /dev/null && echo "✅ Ollama running" || echo "❌ Ollama not running"
If running, you're done. If not, proceed.
# Start Ollama in the background
ollama serve &>/dev/null &
# Wait and verify (2-3 seconds)
sleep 3
curl -sf http://127.0.0.1:11434/api/tags > /dev/null && echo "✅ Ollama ready" || echo "❌ Ollama failed to start"
For RLM distillation, the project uses model you define in .env
# List available models
ollama list
# If the model is missing, pull it
ollama pull qwen2:7b
| Symptom | Fix |
|---|---|
Connection refused after start | Wait longer (sleep 5), model may be loading |
ollama: command not found | Ollama not installed — ask user to install from https://ollama.com |
| Port 11434 already in use | Another process on that port — lsof -i :11434 to identify |
/rlm-factory:distill requires Ollama for batch summarization