Getting Started with Askimo CLI

After installing Askimo, choose a provider and a model, then start chatting. Askimo saves your settings locally, so you won’t need to repeat these steps next time.

👉 If you don’t choose a model, Askimo will use the default for that provider (except Ollama).

Quick start (works the same for any provider)

askimo> :set-provider <ollama|openai|gemini|xai|anthropic|docker|localai|lmstudio>
askimo> :models            # see models available for that provider
askimo> :set-param model <model-id> # optional if a default exists
askimo> "Hello! Summarize this text."

---

Using Ollama (local models)

1. Install Ollama (see ollama.com)
2. Pull a model, for example gpt-oss:20b:

ollama pull gpt-oss:20b

3. In askimo

askimo> :set-provider ollama
askimo> :models          # shows local models (e.g., llama3)
askimo> :set-param model gpt-oss:20b
askimo> "Explain Redis caching in simple terms."

If :models is empty, pull one with ollama pull <name> and try again.

---

Using OpenAI

1. Get an API key → https://platform.openai.com/api-keys
2. Configure Askimo and chat:

askimo> :set-provider openai
askimo> :set-param api_key sk-...
askimo> :models          # e.g., gpt-4o, gpt-4o-mini
askimo> "Explain Redis caching in simple terms."

📌 Default model: gpt-4o

---

Use Gemini (Google)

1. Get an API key → https://aistudio.google.com
2. Configure and chat:

askimo> :provider gemini
askimo> :set-param api_key <your-gemini-key>
askimo> :models                         # e.g., gemini-1.5-pro, gemini-1.5-flash
askimo> "Give me five CLI productivity tips."

📌 Default model: gemini-2.5-flash

---

Use X AI (Grok)

1. Get an API key → https://x.ai
2. Configure and chat:

askimo> :set-provider xai
askimo> :set-param api_key <your-xai-key>
askimo> :models                         # e.g., grok-2, grok-2-mini (examples)
askimo> :set-param model grok-3-mini
askimo> "What's new in Java 21?"

📌 Default model: grok-4

---

Using Anthropic Claude

1. Get an API key → https://console.anthropic.com/
2. Configure and chat:

askimo> :set-provider anthropic
askimo> :set-param api_key <your-anthropic-key>
askimo> :models                         # e.g., claude-3-5-sonnet, claude-3-opus
askimo> "Analyze this code for potential improvements."

📌 Default model: claude-3-5-sonnet-20241022

---

Using Docker AI

1. Enable Docker AI model runner:

docker desktop enable model-runner --tcp 12434

2. Pull a model:

docker model pull ai/gemma3:4B-F16

3. Configure Askimo and chat:

askimo> :set-provider docker
askimo> :models
askimo> :set-param model ai/gemma3:4B-F16
askimo> "Explain containerization concepts."

📌 Default endpoint: http://localhost:12434

---

Using LocalAI

1. Install LocalAI (see localai.io)
2. Configure and chat:

askimo> :set-provider localai
askimo> :set-param base_url http://localhost:8080  # your LocalAI endpoint
askimo> :models                         # shows available LocalAI models
askimo> :set-param model <model-name>
askimo> "Help me debug this function."

---

Using LM Studio

1. Install LM Studio (see lmstudio.ai)
2. Start the local server in LM Studio
3. Configure Askimo and chat:

askimo> :set-provider lmstudio
askimo> :set-param base_url http://localhost:1234  # default LM Studio port
askimo> :models                         # shows loaded models
askimo> :set-param model <model-name>
askimo> "Generate a regex pattern for email validation."

---

Switch any time

You can switch providers/models on the fly; Askimo remembers your last choices.

askimo> :set-provider ollama
askimo> :set-param model mistral
askimo> :set-provider openai