AI & integrations

AI models

Nomima doesn’t lock you into anyone’s AI. Run open models locally with no key at all, or bring your own key for Claude, GPT, Gemini and a dozen more clouds. You pick the provider; Nomima just talks to it.

Your models, your choice. AI in Nomima (the Summon assistant) is free — run a model locally for fully offline use, or supply an API key from any supported cloud. Everything else in Nomima — including the Knowledge Graph, Smart Views and search — works without any AI at all.

Supported providers

Providers come in three groups — the same grouping you’ll see in the picker. Local providers run on your own machine and need no key; the Cloud and OpenAI-compatible groups are bring-your-own-key.

Local — offline, no key

ProviderWhat it isNeeds internet?
OllamaRun open models locally. Stays offline — no key, no cloud.No — runs on your machine
LM StudioLocal models via LM Studio’s server. Offline, no key.No — runs on your machine

Fully offline AI. Point Summon at Ollama or LM Studio and no note ever leaves your Mac — the model runs locally. Summon needs a tool-capable model; the “Check” button confirms a local one qualifies.

Settings · AI model
🦙
Ollama
Local · running on your Mac
Connected
🔓 No API key needed — runs fully offline
Default model
🦙 llama3.1:8b
Installed models
llama3.1:8bSummon-readyDefault
qwen2.5:7bSummon-readyRe-check
phi3:miniSummon · basicCheck
Local providers (Ollama, LM Studio) run offline with no API key — just pick an installed model and confirm it qualifies.

Live status & capability check. For a local provider Nomima shows a green/red server status pill — in Settings and in the Summon header — and lists the models you actually have installed. Picking one runs a one-time capability probe and shows an honest badge: Summon-ready, Summon · basic (a small model), AI blocks only (too weak to drive Summon), or Not checked. If the server is down or the model can’t drive tools, Summon’s composer is disabled with a clear nudge — and even a weak model can still answer from your notes through a grounded, no-tools fallback.

Cloud — bring your own key

ProviderModelsNeeds internet?
AnthropicClaude — Opus, Sonnet, HaikuYes — calls Anthropic with your API key
OpenAIGPT-5.1, GPT-4o and the o-seriesYes — calls OpenAI with your API key
Google GeminiGemini 3 Pro and the Flash tiersYes — calls Google with your API key
AWS BedrockDozens of models on AWS — Claude, GPT-OSS, DeepSeek, Qwen, Mistral and more — from a single Bedrock API keyYes — calls AWS with your Bedrock API key

AWS Bedrock — just paste the key

Bedrock needs a Bedrock API key, not an AWS access key and secret. Create one in the AWS console under Amazon Bedrock → API keys (a long-term key is easiest), then paste it into the single field in Settings → Summon → AI model → AWS Bedrock.

That’s the whole setup — there’s no region to choose. Nomima works out which AWS region your key belongs to on its own and remembers it, then fills the model list live from your own account, so you only ever see models you actually have access to. Pick one and Summon uses it like any other provider.

Two things worth knowing:

If you need Bedrock pinned to a specific region (for data-residency reasons, say), use the change link next to the detected region and enter it yourself.

OpenAI-compatible clouds — bring your own key

These share one OpenAI-compatible adapter, so any of them is just a key away.

ProviderWhat it isNeeds internet?
GroqVery fast inference for open models.Yes — calls Groq with your API key
OpenRouterOne key, hundreds of models across providers.Yes — calls OpenRouter with your API key
MistralMistral’s open + premier models.Yes — calls Mistral with your API key
DeepSeekDeepSeek’s chat + reasoning models.Yes — calls DeepSeek with your API key
xAI (Grok)Grok models from xAI.Yes — calls xAI with your API key
Together AIOpen models hosted on Together AI.Yes — calls Together with your API key

Setting up a provider

  1. Open Settings → Summon → AI model. It’s a two-pane view: the provider list (grouped Local / Cloud / OpenAI-compatible) on the left, the selected provider’s detail on the right.
  2. Pick a provider. For a local one (Ollama, LM Studio) there’s no key — Nomima probes for the models you have installed. For a cloud one, paste your API key.
  3. Choose a model. For local providers this is whatever you’ve pulled; for clouds it’s the models that provider offers.
  4. Confirm it works — a small test call checks the credentials, and Check verifies a local model is tool-capable enough for Summon.
  5. Set your default provider; that’s what Summon uses unless told otherwise.
Settings · AI model
Local
🦙 Ollama
🎛️ LM Studio
Cloud
✳️ Anthropic
⚙️ OpenAI
Gemini
OpenAI-compatible
Groq
🔀 OpenRouter
🌫️ Mistral
Anthropic
Claude — Opus, Sonnet, Haiku
API key
sk-ant-••••••••••••••4c2a👁
Model
Claude Opus 4.8
Test connection ✓ Connected
One page for every provider: pick from the grouped left rail, then paste a key, choose a model and test the connection on the right.

How your keys are protected

What actually uses AI

FeatureUses your AI model?
Summon assistantYes — the only feature that calls your AI model
Knowledge Graph, briefs, themesNo — built with on-device analysis
Search, Smart Views, Home agendaNo
Date detection, smart tagsNo

If you never configure a provider, Nomima simply never makes an AI call. The app is fully functional as a private, offline notebook.

If something fails

Nomima tells you exactly what went wrong rather than failing silently: an invalid key (fix the key), quota exhausted (top up with your provider), rate limited (wait a moment and retry), or a network error (check your connection).