[🤖 Agents](./agents.md) are powered by a provider. The provider could be a **local service** or a **cloud service**.
The list of supported providers is below.
### Table of contents
- [How to choose a provider](#how-to-choose-a-provider)
- [How to use a provider](#how-to-use-a-provider)
- [Supported providers](#supported-providers)
- [Anthropic](#anthropic)
- [Groq](#groq)
- [LocalAI](#localai)
- [Mistral](#mistral)
- [Ollama](#ollama)
- [OpenAI](#openai)
- [OpenAI Compatible](#openai-compatible)
- [OpenRouter](#openrouter)
- [Together AI](#together-ai)
### How to choose a provider
If you're not sure which provider to start with, we **recommend [OpenAI](#openai)** as it's the most popular and has the **widest range of capabilities**: [💬 text-generation](./features.md#-text-generation), [🖌️ image-generation](./features.md#️-image-generation), [🦻 speech-to-text](./features.md#-speech-to-text), [🗣️ text-to-speech](./features.md#️-text-to-speech).
You don't need to choose just one though. The bot supports [mixing & matching models](./features.md#-mixing--matching-models), so you can use multiple providers at the same time.
### How to use a provider
- sign up for it
- obtain an API key
- [create a new agent](./agents.md#creating-agents)
- set it as a handler for some types of messages (see [Mixing & matching models](./features.md#-mixing--matching-models)) for a specific room or globally
### Supported providers
### Anthropic
[Anthropic](https://www.anthropic.com/) is an American AI company founded by former OpenAI engineers and providing powerful language models.
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/anthropic.yml).
[Groq](https://groq.com/) is an American company developing optimized Language Processing Units (LPU) and offering cloud service which runs various models (built by others) with very high performance.
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/groq.yml).
[LocalAI](https://localai.io/) is the free, Open Source OpenAI alternative. LocalAI act as a drop-in replacement REST API that’s compatible with OpenAI API specifications for local inferencing. It allows you to run LLMs, generate images, audio (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families and architectures.
- 🆔 Identifier: `localai`
- 🔗 Links: [🏠 Home page](https://localai.io/), [📋 Models list](https://localai.io/gallery.html)
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/localai.yml).
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/mistral.yml).
[Ollama](https://ollama.com/) lets you run various models in a [self-hosted](https://github.com/ollama/ollama?tab=readme-ov-file#ollama) way. This is more advanced and requires powerful hardware for running some of the better models, but ensures your data stays with you.
- 🆔 Identifier: `ollama`
- 🔗 Links: [🏠 Home page](https://ollama.com/), [📋 Models list](https://ollama.com/library)
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/ollama.yml).
[OpenAI](https://openai.com/) is an American AI company providing powerful language models.
Use this provider either with the OpenAI API or with other OpenAI-compatible API services which **fully** adhere to the [OpenAI API spec](https://github.com/openai/openai-openapi/).
For services which are not fully compatible with the OpenAI API, consider using the [OpenAI Compatible](#openai-compatible) provider.
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/openai.yml).
This provider allows you to use OpenAI-compatible API services like [OpenRouter](https://openrouter.ai/), [Together AI](https://www.together.ai/), etc.
Some of these popular services already have **shortcut** providers (leading to this one behind the scenes) - this make it easier to get started.
This provider is just as featureful as the [OpenAI](#openai) provider, but is more compatible with services which do not fully adhere to the [OpenAI API spec](https://github.com/openai/openai-openapi/).
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/openai-compatible.yml).
[OpenRouter](https://openrouter.ai/) is a unified interface for LLMs. The platform scouts for the lowest prices and best latencies/throughputs across dozens of providers, and lets you choose how to [prioritize](https://openrouter.ai/docs/provider-routing) them.
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/openrouter.yml).
[Together AI](https://www.together.ai/) makes it easy to run or [fine-tune](https://docs.together.ai/docs/fine-tuning-overview) leading open source models with only a few lines of code.
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/together-ai.yml).