> For the complete documentation index, see [llms.txt](https://djthorpe.gitbook.io/go-llm/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://djthorpe.gitbook.io/go-llm/getting-started.md).

# Getting Started

Once go-llm is running, and the command line is installed (see [Installation](/go-llm/installation.md)), add providers, and start a conversation.

## Add providers

Add providers in the web UI, with **Add provider** on the Models page, or with the command line:

```bash
llm provider-create-ollama http://host.docker.internal:11434
llm provider-create-lmstudio http://host.docker.internal:1234/v1
llm provider-create-openai --api-key-credential OPENAI_API_KEY
llm provider-create-anthropic --api-key-credential ANTHROPIC_API_KEY
llm provider-create-gemini --api-key-credential GEMINI_API_KEY

llm providers
llm models
```

* **API keys** are given by the name of the server's environment variable, so the key itself is never stored or sent.
* **URLs** are as the server sees them, rather than the machine running `llm`.

See [Models and Providers](/go-llm/models-and-providers.md) for every provider.

## Ask, and chat

```bash
llm ask --model gpt-4o-mini "Explain a KV cache in two sentences"
llm ask --attach main.go "What does this do?"

llm session-create --model ollama:llama3.2 --system "Be brief" --tools "weatherapi:*"
llm chat                                        # in the terminal
llm chat "Will it rain in Berlin tomorrow?"     # once
```

Or chat in the web UI, with **Add conversation**. See [Conversations and Tasks](/go-llm/conversations-and-tasks.md).

## Commands

| Group            | Commands                                                                                                                                                                                                                                                                                                                                        |
| ---------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Server           | `run`, `openapi`                                                                                                                                                                                                                                                                                                                                |
| Providers        | `providers`, `provider`, `provider-create-ollama`, `provider-create-lmstudio`, `provider-create-openai`, `provider-create-anthropic`, `provider-create-gemini`, `provider-create-mistral`, `provider-create-deepseek`, `provider-create-gowhisper`, `provider-create-elevenlabs`, `provider-create-eliza`, `provider-update`, `provider-delete` |
| Models           | `models`, `model`, `model-load`, `model-delete`, `model-unload`, `model-voices`                                                                                                                                                                                                                                                                 |
| Sessions         | `sessions`, `session`, `session-messages`, `session-create`, `session-update`, `session-forget`, `session-compact`, `session-delete`                                                                                                                                                                                                            |
| Inference        | `ask`, `chat`, `embed`, `ocr`, `transcribe`, `translate`, `speak`, `illustrate`                                                                                                                                                                                                                                                                 |
| Tools and agents | `namespaces`, `tools`, `tool`, `call`, `agents`, `agent`, `agent-create`, `agent-update`, `agent-delete`                                                                                                                                                                                                                                        |
| Connectors       | `connectors`, `connector`, `connector-create`, `connector-update`, `connector-delete`                                                                                                                                                                                                                                                           |
| Memory           | `details`, `detail-set`, `detail-forget`, `memories`, `memory`, `memory-remember`, `memory-forget`                                                                                                                                                                                                                                              |
| Heartbeats       | `heartbeats`, `heartbeat`, `heartbeat-create`, `heartbeat-update`, `heartbeat-delete`                                                                                                                                                                                                                                                           |
| Resources        | `resources`, `resource`, `resource-create`, `resource-get`, `resource-delete`                                                                                                                                                                                                                                                                   |
| Events           | `events`                                                                                                                                                                                                                                                                                                                                        |

Run `llm <command> --help` for its flags. Model options are given with `--opt`, such as `--opt temperature=0.2`. These options control the agent loop rather than the model:

| Option           | Default            | Meaning                                                |
| ---------------- | ------------------ | ------------------------------------------------------ |
| `max_iterations` | 10, or 3 for `ask` | How many times the model is asked before it must reply |
| `max_depth`      | 3                  | How deeply agents can call agents                      |
| `tool_timeout`   | `30s`              | How long a tool has to return                          |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://djthorpe.gitbook.io/go-llm/getting-started.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.