Create a Conversation

Open AfferLab and click New Conversation in the sidebar.

Choose a model and a strategy, then start chatting.

---

Configure a Model

Before sending a message, you need to configure at least one model. Go to Settings → Models and find your provider. Turn on the toggle next to the models you want to use.

Only enabled models will appear in the model selector in the chat input.

Common options include:

• API-based providers (OpenAI, Anthropic, etc.)
• Local model servers such as Ollama or LM Studio (the server must be running)

---

Choose a Strategy

Every AfferLab conversation runs with a strategy. A strategy defines how the conversation works, including how context is built and how memory may be used.

AfferLab includes several built-in strategies:

Standard Chat: A simple conversational strategy focused on natural dialogue.

Research Assistant: Optimized for gathering and summarizing information.

Memory Chat: Enables long-term knowledge storage and retrieval during conversations.

You can switch strategies at any time in the conversation settings.