fix: add all model providers markdown and fix typos (#1)

Author: dbschmigelski

README.md

@@ -71,7 +71,7 @@ In `~/.cursor/mcp.json`:
 ## Server development
 
 ```bash
-git clone git@github.com:strands-agents/mcp-server.git
+git clone https://github.com/strands-agents/mcp-server.git
 cd mcp-server
 python3 -m venv venv
 source venv/bin/activate

pyproject.toml

@@ -39,7 +39,7 @@ allow-direct-references = true
 [project.urls]
 Homepage = "https://github.com/strands-agents/mcp-server"
 "Bug Tracker" = "https://github.com/strands-agents/mcp-server"
-Documentation = "https://www.strands-agents.com"
+Documentation = "https://strandsagents.com"
 
 [project.optional-dependencies]
 dev = [

src/strands_mcp_server/content/model_providers.md

@@ -67,53 +67,79 @@ anthropic_model = AnthropicModel(
 agent = Agent(model=anthropic_model)
 ```
 
-### Ollama (Local Models)
+### LiteLLM
 
-First install the `ollama` python client:
+LiteLLM is a unified interface for various LLM providers that allows you to interact with models from OpenAI and many others.
+
+First install the `litellm` python client:
 
 ```bash
-pip install strands-agents[ollama]
+pip install strands-agents[litellm]
 ```
 
-Next, import and initialize the `OllamaModel` provider:
+Next, import and initialize the `LiteLLMModel` provider:
 
 ```python
 from strands import Agent
-from strands.models.ollama import OllamaModel
+from strands.models.litellm import LiteLLMModel
 
-ollama_model = OllamaModel(
-    host="http://localhost:11434"  # Ollama server address
-    model_id="llama3",  # Specify which model to use
-    temperature=0.3,
+litellm_model = LiteLLMModel(
+    client_args={
+        "api_key": "<KEY>",
+    },
+    model_id="gpt-4o"
 )
 
-agent = Agent(model=ollama_model)
+agent = Agent(model=litellm_model)
 ```
 
-### LiteLLM
+### Llama API
 
-LiteLLM is a unified interface for various LLM providers that allows you to interact with models from OpenAI and many others.
-
-First install the `litellm` python client:
+Llama API is a Meta-hosted API service that helps you integrate Llama models into your applications quickly and efficiently.
 
+First install the `` python client:
 ```bash
-pip install strands-agents[litellm]
+pip install strands-agents[llamaapi]
 ```
 
-Next, import and initialize the `LiteLLMModel` provider:
+Next, import and initialize the `LlamaAPIModel` provider:
 
 ```python
 from strands import Agent
-from strands.models.litellm import LiteLLMModel
+from strands.models.llamaapi import LLamaAPIModel
 
-litellm_model = LiteLLMModel(
+model = LlamaAPIModel(
     client_args={
         "api_key": "<KEY>",
     },
-    model_id="gpt-4o"
+    # **model_config
+    model_id="Llama-4-Maverick-17B-128E-Instruct-FP8",
 )
 
-agent = Agent(model=litellm_model)
+agent = Agent(models=LLamaAPIModel)
+```
+
+### Ollama (Local Models)
+
+First install the `ollama` python client:
+
+```bash
+pip install strands-agents[ollama]
+```
+
+Next, import and initialize the `OllamaModel` provider:
+
+```python
+from strands import Agent
+from strands.models.ollama import OllamaModel
+
+ollama_model = OllamaModel(
+    host="http://localhost:11434"  # Ollama server address
+    model_id="llama3",  # Specify which model to use
+    temperature=0.3,
+)
+
+agent = Agent(model=ollama_model)
 ```
 
 ### Custom Model Providers