diff --git a/DOCS/agents/README.md b/DOCS/agents/README.md
index c45d390f..c30fd7d2 100644
--- a/DOCS/agents/README.md
+++ b/DOCS/agents/README.md
@@ -1,7 +1,30 @@
+# Agents
+Agents are individual building blocks in a swarm, they each have a driving force in our case a language model, with long term memory and the capacity to use tools in other words an agent is:
+
+LLM => Long Term Memory => Tools
+
+That's it.
+
+That's as simple as it can get.
+
+Our Agent classes have to be as simple as humanely possible, they should be plug in and play with any of language model classes, vectorstores, and tools. 
+
+## File structure
+```
+* memory
+* models
+* tools 
+* utils
+* mem
+```
+
+
 # Swarms Documentation
+
 ====================
 
 ## Language Models
+
 ---------------
 
 Language models are the driving force of our agents. They are responsible for generating text based on a given prompt. We currently support two types of language models: Anthropic and HuggingFace.
@@ -13,55 +36,72 @@ The `Anthropic` class is a wrapper for the Anthropic large language models.
 #### Initialization
 
 ```
+
 Anthropic(model="claude-2", max_tokens_to_sample=256, temperature=None, top_k=None, top_p=None, streaming=False, default_request_timeout=None)
+
 ```
 
-Copy code
+
 
 ##### Parameters
 
--   `model` (str, optional): The name of the model to use. Default is "claude-2".
--   `max_tokens_to_sample` (int, optional): The maximum number of tokens to sample. Default is 256.
--   `temperature` (float, optional): The temperature to use for the generation. Higher values result in more random outputs.
--   `top_k` (int, optional): The number of top tokens to consider for the generation.
--   `top_p` (float, optional): The cumulative probability of parameter highest probability vocabulary tokens to keep for nucleus sampling.
--   `streaming` (bool, optional): Whether to use streaming mode. Default is False.
--   `default_request_timeout` (int, optional): The default request timeout in seconds. Default is 600.
+- `model` (str, optional): The name of the model to use. Default is "claude-2".
+
+- `max_tokens_to_sample` (int, optional): The maximum number of tokens to sample. Default is 256.
+
+- `temperature` (float, optional): The temperature to use for the generation. Higher values result in more random outputs.
+
+- `top_k` (int, optional): The number of top tokens to consider for the generation.
+
+- `top_p` (float, optional): The cumulative probability of parameter highest probability vocabulary tokens to keep for nucleus sampling.
+
+- `streaming` (bool, optional): Whether to use streaming mode. Default is False.
+
+- `default_request_timeout` (int, optional): The default request timeout in seconds. Default is 600.
 
 ##### Example
 
 ```
+
 anthropic = Anthropic(model="claude-2", max_tokens_to_sample=100, temperature=0.8)
+
 ```
 
-Copy code
+
 
 #### Generation
 
 ```
+
 anthropic.generate(prompt, stop=None)
+
 ```
 
-Copy code
+
 
 ##### Parameters
 
--   `prompt` (str): The prompt to use for the generation.
--   `stop` (list, optional): A list of stop sequences. The generation will stop if one of these sequences is encountered.
+- `prompt` (str): The prompt to use for the generation.
+
+- `stop` (list, optional): A list of stop sequences. The generation will stop if one of these sequences is encountered.
 
 ##### Returns
 
--   `str`: The generated text.
+- `str`: The generated text.
 
 ##### Example
 
 ```
+
 prompt = "Once upon a time"
+
 stop = ["The end"]
+
 print(anthropic.generate(prompt, stop))
+
 ```
 
-Copy code
+
 
 ### HuggingFaceLLM
 
@@ -70,47 +110,98 @@ The `HuggingFaceLLM` class is a wrapper for the HuggingFace language models.
 #### Initialization
 
 ```
+
 HuggingFaceLLM(model_id: str, device: str = None, max_length: int = 20, quantize: bool = False, quantization_config: dict = None)
+
 ```
 
-Copy code
+
 
 ##### Parameters
 
--   `model_id` (str): The ID of the model to use.
--   `device` (str, optional): The device to use for the generation. Default is "cuda" if available, otherwise "cpu".
--   `max_length` (int, optional): The maximum length of the generated text. Default is 20.
--   `quantize` (bool, optional): Whether to quantize the model. Default is False.
--   `quantization_config` (dict, optional): The configuration for the quantization.
+- `model_id` (str): The ID of the model to use.
+
+- `device` (str, optional): The device to use for the generation. Default is "cuda" if available, otherwise "cpu".
+
+- `max_length` (int, optional): The maximum length of the generated text. Default is 20.
+
+- `quantize` (bool, optional): Whether to quantize the model. Default is False.
+
+- `quantization_config` (dict, optional): The configuration for the quantization.
 
 ##### Example
 
 ```
+
 huggingface = HuggingFaceLLM(model_id="gpt2", device="cpu", max_length=50)
+
 ```
 
-Copy code
+
 
 #### Generation
 
 ```
+
 huggingface.generate(prompt_text: str, max_length: int = None)
+
 ```
 
-Copy code
+
 
 ##### Parameters
 
--   `prompt_text` (str): The prompt to use for the generation.
--   `max_length` (int, optional): The maximum length of the generated text. If not provided, the default value specified during initialization is used.
+- `prompt_text` (str): The prompt to use for the generation.
+
+- `max_length` (int, optional): The maximum length of the generated text. If not provided, the default value specified during initialization is used.
 
 ##### Returns
 
--   `str`: The generated text.
+- `str`: The generated text.
 
 ##### Example
 
 ```
+
+prompt = "Once upon a time"
+
+print(huggingface.generate(prompt))
+
+```
+
+
+### Full Examples
+
+```python
+# Import the necessary classes
+
+from swarms import Anthropic, HuggingFaceLLM
+
+# Create an instance of the Anthropic class
+
+anthropic = Anthropic(model="claude-2", max_tokens_to_sample=100, temperature=0.8)
+
+# Use the Anthropic instance to generate text
+
 prompt = "Once upon a time"
+
+stop = ["The end"]
+
+print("Anthropic output:")
+
+print(anthropic.generate(prompt, stop))
+
+# Create an instance of the HuggingFaceLLM class
+
+huggingface = HuggingFaceLLM(model_id="gpt2", device="cpu", max_length=50)
+
+# Use the HuggingFaceLLM instance to generate text
+
+prompt = "Once upon a time"
+
+print("\nHuggingFaceLLM output:")
+
 print(huggingface.generate(prompt))
-```
\ No newline at end of file
+
+```
+