Search for a command to run...
Articles tagged with #ollama
You spend an hour crafting the perfect persona. A meticulous project manager. Formal tone. No code unless asked. Clear status updates. You load it into Claude Opus. It works beautifully. The agent stays in character, follows every instruction, mainta...
한 시간을 들여 완벽한 페르소나를 만들었다. 꼼꼼한 프로젝트 매니저. 격식체. 요청 없으면 코드 작성 금지. 명확한 상태 보고. Claude Opus에 넣었더니 완벽하게 동작한다. 에이전트가 캐릭터를 유지하고, 모든 지시사항을 따르고, 긴 대화에서도 페르소나가 흔들리지 않는다. 같은 페르소나를 로컬 모델 — Llama 3.2, Qwen3-Coder, Mistral — Ollama로 돌려봤다. 3번째 메시지에서 또 코드를 짜고 있다. 페르소나가 ...
You spend an hour crafting the perfect persona. A meticulous project manager. Formal tone. No code unless asked. Clear status updates. You load it into Claude Opus. It works beautifully. The agent stays in character, follows every instruction, mainta...
What You'll Build A locally-running AI agent that doesn't just answer questions — it has a personality, opinions, and a consistent voice. No cloud API keys. No subscriptions. Everything runs on your machine. The stack is three layers: LayerWhat I...
Ollama just shipped version 0.17, and buried in the release is something quietly significant: native OpenClaw integration. One command: ollama launch openclaw That's it. Your local open-weight model is now connected to an agent framework with tool u...