Ollama — run AI locally with screenpipe

Ollama lets you run AI models locally on your machine. screenpipe integrates natively with Ollama — no API keys, no cloud, completely private.

setup

1. install Ollama & pull a model

# install from https://ollama.com then:
ollama run ministral-3

this downloads the model and starts Ollama. you can use any model — ministral-3 is a good starting point (fast, works on most machines).

2. select Ollama in screenpipe

1. open the screenpipe app
2. click the AI preset selector (top of the chat/timeline)
3. click Ollama
4. pick your model from the dropdown (screenpipe auto-detects pulled models)
5. start chatting

that's it. screenpipe talks to Ollama on localhost:11434 automatically.

recommended models

pull any model with:

ollama pull <model-name>

requirements

• Ollama installed and running
• at least one model pulled
• screenpipe running

custom OpenAI-compatible endpoints

if you're running a custom LLM server (Qwen, vLLM, Text Generation WebUI, etc.), screenpipe auto-detects the endpoint format:

1. first tries OpenAI-compatible format: GET {endpoint}/v1/models
2. falls back to Ollama format: GET {endpoint}/api/tags

if your endpoint uses neither format, you may need to:

• check what path your server uses for model listing (/models, /v1/list, etc.)
• if unsure, test with curl first: curl {your-endpoint}/path-to-models
• join our Discord — we can help troubleshoot custom setups

example: a Qwen server on http://localhost:5000 with OpenAI-compatible API should work automatically. if screenpipe can't find models, verify the server responds to: curl http://localhost:5000/v1/models

troubleshooting

"ollama not detected"

• make sure Ollama is running: ollama serve
• check it's responding: curl http://localhost:11434/api/tags

model not showing in dropdown?

• pull it first: ollama pull ministral-3
• you can also type the model name manually in the input field

slow responses?

• try a smaller model (ministral-3)
• close other GPU-heavy apps
• ensure you have enough free RAM (model size + ~2 GB overhead)

need help? join our discord — get recommendations on models and configs from the community.