TotalApp Docs

Agentic Overview

How TotalApp routes agentic text generation and embeddings across five engines — Ollama, local Ollama models, in-browser models, cloud APIs, and embedding models — all configured from Settings → Agentic.

What Lives Under Agentic

The Agentic section documents every engine and model catalog available from Settings → Agentic. Two independent choices exist on that screen: the AI Engine (what generates text) and the Embedding Engine (what powers Semantic Search ranking) — they're configured separately and can be mixed freely.

Where to configure it

Go to Settings → Agentic to choose an AI Engine and, independently, an Embedding Engine. See Agentic AI Settings for the full settings reference.

The Four AI Engines

Choosing an AI Engine decides where your text-generation requests actually run:

EngineRuns onRequiresDocs page
OllamaYour own machine (local server process)Ollama installed & runningOllama Integration, Local Language Models
In-Browser LLM (WebGPU)The browser tab itself (WebGPU/WASM)Nothing — model downloads once and is cached by the browserIn-Browser Models
Cloud LLM (Hosted API)A third-party provider's serversAn API key per providerCloud LLM Models
Local CLIYour own machine, via the installed claude CLIClaude CLI installed & authenticatedAgentic AI Settings

Ollama Integration

TotalApp integrates with Ollama, a local model runner — both text generation and embeddings can run entirely on your own machine, with no traffic ever reaching TotalApp's server. See Ollama Integration for the full explanation of how the browser talks directly to your local Ollama instance.

Local Language Models (Ollama)

Once Ollama is running, Local Language Models catalogs the downloadable text-generation models, grouped by what they're best at:

General Purpose

mistral, llama3.3, gemma2 — the safest default for everyday chat and writing.

Reasoning & Heavy Tasks

deepseek-r1, qwen2.5, phi4 — code, math, and multi-step logic.

Lightweight & Micro

llama3.2:1b, llama3.2, phi3 — low-powered machines or fast background tasks.

In-Browser Models

No Ollama install needed at all: In-Browser Models run directly inside the browser tab's own memory and GPU (via WebGPU, falling back to WASM), using Transformers.js. Nothing is installed outside the browser.

Micro / Low-Resource

SmolLM2-135M, SmolLM2-360M, Qwen2.5-0.5B — old or GPU-less machines.

Balanced In-Browser

TinyLlama-1.1B, Llama-3.2-1B-Instruct, SmolLM2-1.7B — everyday in-browser writing and chat.

High Performance

Qwen2.5-1.5B-Instruct, Qwen2.5-Coder-1.5B — best in-browser reasoning and code quality.

Cloud LLM Models

Cloud LLM Models catalogs every hosted provider, grouped by architecture:

ArchitectureProvidersNotes
DirectAnthropic, OpenAI, Google AI Studio, DeepSeekLowest latency/cost for that provider's own models.
Proxy / Router & ServerlessCohere, GroqManaged infrastructure; Groq specializes in very high inference speed for open models.
AggregatorOpenRouterOne API key, many providers — usually a small markup over calling directly.

Embedding Models

Independent of the AI Engine, TotalApp uses local Ollama models exclusively for embeddings — used to rank and retrieve knowledge sources for Semantic Search. See Embedded Models for the full catalog, recommended starting points (nomic-embed-text for long English context, bge-m3 for multilingual/Turkish), and download instructions.

Choosing an Engine

Want full privacy, have a capable machine?

Use Ollama with a model from Local Language Models.

Want zero install, quick trial?

Use In-Browser Models — nothing to set up outside the browser.

Want the strongest models available?

Use Cloud LLM Models with an API key from your preferred provider.

FAQ

Do I have to pick the same engine for text generation and embeddings?
No. The AI Engine and Embedding Engine are configured independently — you can generate content via a Cloud LLM provider while still using a local Ollama model purely for embeddings, or any other combination.
Which engine should I start with?
If you're not sure, In-Browser Models require no setup at all and are a good first try. For production use with the best quality, Cloud LLM Models (Anthropic, OpenAI, etc.) are typically strongest; for full privacy, Ollama.
Can I switch engines later?
Yes. The AI Engine dropdown in Settings → Agentic can be changed at any time — no data migration is required since each engine is stateless per request.
What's the difference between Ollama and Local CLI?
Both run entirely on your own machine, but Ollama talks to a local model-runner server process you install separately, while Local CLI routes requests through an already-installed and authenticated claude CLI — no separate server to manage.
Does any engine send my data to TotalApp's servers?
No engine choice routes text-generation traffic through TotalApp's own servers. Ollama and Local CLI stay entirely on your machine; In-Browser Models never leave the browser tab; Cloud LLM sends requests directly from your browser to the provider you configured using your own API key.
Why would I choose In-Browser Models over Ollama?
In-Browser Models need no install at all — the model downloads once and is cached by the browser, which makes them the fastest way to try TotalApp's AI features. Ollama requires installing and running a separate application, but supports larger, more capable models.
Do I need an API key for every Cloud LLM provider?
You only need a key for the specific provider you select — Anthropic, OpenAI, Google AI Studio, DeepSeek, Cohere, Groq, or OpenRouter. Switching providers later just means adding that provider's key in Settings → Agentic.
Why are embeddings always local, even when I use a Cloud LLM for text generation?
TotalApp uses local Ollama models exclusively for embeddings so that the knowledge sources indexed for Semantic Search never have to leave your machine, regardless of which AI Engine you pick for text generation.