Local and cloud model execution
Run models on your own hardware for offline or local workflows, with cloud models available when you need larger or faster systems.
Ollama
Freemium
Exécutez des modèles ouverts en local ou dans le cloud pour le code, l’automatisation, l’analyse et les agents.
Qu'est-ce que Ollama ?
Ollama is a platform for working with open models locally or in the cloud. The site positions it as a way to automate work with open models while keeping data private, and it supports workflows ranging from simple chat to coding, document analysis, and agent tasks.
The product combines local model execution with cloud access for larger or faster models. Its site surface includes model browsing, a download flow for desktop installation, documentation for integrations and APIs, and pricing tiers that separate unlimited local hardware use from metered cloud usage.
Que peut faire Ollama ?
Model discovery and selection
Choose from models for chat, coding, vision, embeddings, reasoning, and agentic workflows through the site’s model browsing experience.
Multiple access surfaces
Use Ollama through the CLI, API, desktop apps, and libraries, with documentation for integrations and first API requests.
App and agent integrations
Connect Ollama to apps, editors, and agents, including workflows highlighted on the home page for tools such as Claude Code and other agents.
Tool-aware cloud models
Access cloud models that are tested for tool calling and real agent workflows before release, according to the pricing FAQ.
Usage tiers for cloud work
Use paid cloud plans for heavier workloads, including concurrent model runs and larger models, while keeping local runs unlimited on your own hardware.
Cas d'utilisation
“Local private workflows”
Run open models on a local machine when you need offline operation or want to keep sensitive work on your own hardware.
“Heavier cloud-assisted work”
Use cloud models for coding automation, document analysis, and other tasks that benefit from larger or faster models.
“Integrating with tools and products”
Connect Ollama to an app, editor, or agent through the documented integration and API paths to build model-powered workflows.
“Choosing models for a task”
Browse available models for chat, coding, vision, embeddings, and reasoning when selecting a model for a specific task.
“Continuous multi-model sessions”
Use paid plans for sustained work that needs multiple concurrent models or higher usage limits.
Questions fréquentes
Can I use Ollama locally and in the cloud?
Ollama supports running models locally on your own hardware, and its documentation also points to cloud models for larger workloads. The pricing page notes local hardware usage is unlimited, while cloud usage depends on the plan.
How do I connect Ollama to other tools?
The site says Ollama can connect to apps, editors, and agents, and its documentation includes integrations plus API references and Python and JavaScript libraries.
Do Ollama cloud models support tool calling?
The pricing page says cloud models that support tools are tested for tool calling and real agent workflows before they go live.
What platforms can I install Ollama on?
The download page offers installers for macOS, Linux, and Windows, and the Windows page notes Windows 10 or later is required.
Does Ollama train on my data?
No. The pricing page states that prompt or response data is never logged or trained on, and the home page says your data stays yours.
Informations rapides
- Category
- AI platform
- Primary use
- Run open models for automation, coding, analysis, and agents
- Access
- Local hardware plus cloud models
- Platforms
- macOS, Linux, Windows
- Source domain
- ollama.com
- Pricing
- Free local use; paid Pro and Max cloud plans; Team coming soon
Analyse du trafic de Ollama
Les données de trafic sont fournies à titre indicatif uniquement.
- Évaluation du domaine
- 89
Alternatives à Ollama
OpenCode Superapp
opencodesuper.app
OpenCode Superapp est un espace de travail natif pour Mac qui permet d’utiliser des modèles d’IA locaux, auto-hébergés ou dans le cloud, avec du code, de l’automatisation du navigateur, la voix, des extensions, des widgets et un accès à distance sécurisé. Il s’adresse aux personnes qui souhaitent un environnement OpenCode privilégiant le local, sans compte.
DevSwat
dev-swat.com
DevSwat est une plateforme d’infrastructure d’IA agentique pour créer, exécuter et planifier des agents d’IA autonomes. Elle réunit un IDE dans le navigateur, le chat, l’automatisation des workflows, l’analyse du code et des contrôles de gouvernance dans un environnement web unique.
E2B
e2b.dev
E2B exécute des agents IA dans des sandboxes isolés avec des SDK Python et JavaScript pour la recherche, le code et l’analyse de données.
Tensorlake
tensorlake.ai
Cloud sandbox-native pour agents IA exécutant du code non fiable dans des microVM isolées
1Code
1code.dev
1Code est un client visuel open source pour agents de programmation, réunissant Claude Code et Codex avec des flux desktop et web, des revues et fusions Git, et des exécutions en arrière-plan dans le cloud.
Clark Labs
www.clarkchat.com
Clark Labs propose Clark Agent pour les tâches web autonomes dans le cloud et Clark Code pour les tâches de programmation en local ou via SSH. La plateforme fournit également une passerelle API compatible avec OpenAI pour appeler les modèles Clark ou acheminer des modèles de pointe via Clark.