fix typos (#7123)

* fix typos in various places

* Revert changes to NOTICES

---------

Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>

README.md

@@ -43,7 +43,7 @@ This guide will walk you through the process of creating your own agent and usin
 
 **Makes agents easy to use!** The `frontend` gives you a user-friendly interface to control and monitor your agents. It connects to agents through the [agent protocol](#-agent-protocol), ensuring compatibility with many agents from both inside and outside of our ecosystem.
 
-<!-- TODO: instert screenshot of front end -->
+<!-- TODO: insert screenshot of front end -->
 
 The frontend works out-of-the-box with all agents in the repo. Just use the [CLI] to run your agent of choice!
 

autogpt/tests/unit/test_json.py

@@ -31,7 +31,7 @@ _JSON_FIXABLE: list[tuple[str, str]] = [
         '```json\n{"name": "John Doe", "age": 30}\n```',
         '{"name": "John Doe", "age": 30}',
     ),
-    # Mutliple problems
+    # Multiple problems
     (
         '{"name":"John Doe" "age": 30\n "empty": "","address": '
         "// random comment\n"

benchmark/agbenchmark/challenges/CHALLENGE.md

@@ -26,7 +26,7 @@ Example:
 ```json
 {
   "category": ["basic"],
-  "task": "Print the the capital of America to a .txt file",
+  "task": "Print the capital of America to a .txt file",
   "dependencies": ["TestWriteFile"], // the class name of the test
   "ground": {
     "answer": "Washington",
@@ -57,7 +57,7 @@ This is the default method of evaluation. It will compare the files specified in
 
 ### python
 
-This runs a python function in the specified "files" which captures the the print statements to be scored using the "should_contain" and "should_not_contain" ground truths.
+This runs a python function in the specified "files" which captures the print statements to be scored using the "should_contain" and "should_not_contain" ground truths.
 
 ### llm
 

benchmark/agbenchmark/utils/dependencies/__init__.py

@@ -146,7 +146,7 @@ def pytest_configure(config: Any) -> None:
     # Register marker
     config.addinivalue_line(
         "markers",
-        "depends(name='name', on=['other_name']): marks depencies between tests.",
+        "depends(name='name', on=['other_name']): marks dependencies between tests.",
     )
 
 

docs/content/forge/components/creating-components.md

@@ -93,12 +93,13 @@ To learn more about commands see [🛠️ Commands](./commands.md).
 
 After components provided all necessary data, the agent needs to build the final prompt that will be send to a llm.
 Currently, `PromptStrategy` (*not* a protocol) is responsible for building the final prompt.
-If you want to change the way the prompt is built, you need to create a new `PromptStrategy` class, and then call relavant methods in your agent class.
+
+If you want to change the way the prompt is built, you need to create a new `PromptStrategy` class, and then call relevant methods in your agent class.
 You can have a look at the default strategy used by the AutoGPT Agent: [OneShotAgentPromptStrategy](https://github.com/Significant-Gravitas/AutoGPT/tree/master/autogpt/autogpt/agents/prompt_strategies/one_shot.py), and how it's used in the [Agent](https://github.com/Significant-Gravitas/AutoGPT/tree/master/autogpt/autogpt/agents/agent.py) (search for `self.prompt_strategy`).
 
 ## Example `UserInteractionComponent`
 
-Let's create a slighlty simplified version of the component that is used by the built-in agent.
+Let's create a slightly simplified version of the component that is used by the built-in agent.
 It gives an ability for the agent to ask user for input in the terminal.
 
 1. Create a class for the component that inherits from `CommandProvider`.

forge/forge/agent/base.py

@@ -287,7 +287,7 @@ class BaseAgent(Generic[AnyProposal], metaclass=AgentMeta):
                         f"Component {component.__class__.__name__} "
                         "is attached to an agent but not added to components list"
                     )
-            # Skip collecting anf sorting and sort if ordering is explicit
+            # Skip collecting and sorting and sort if ordering is explicit
             return
         self.components = self._topological_sort(components)
 

forge/forge/agent/components.py

@@ -43,9 +43,9 @@ class ComponentEndpointError(Exception):
 
 
 class EndpointPipelineError(ComponentEndpointError):
-    """Error of an entire pipline of one endpoint."""
+    """Error of an entire pipeline of one endpoint."""
 
 
 class ComponentSystemError(EndpointPipelineError):
     """Error of a group of pipelines;
-    multiple different enpoints."""
+    multiple different endpoints."""

forge/tutorials/001_getting_started.md

@@ -84,7 +84,7 @@ This command forcefully stops the agent. You can also restart it using the start
 ## To Recap
 - We've forked the AutoGPT repo and cloned it locally on your machine.
 - we connected the library with our personal github access token as part of the setup.
-- We've run the agent and it's tasking server successfully without an error.
+- We've run the agent and its tasking server successfully without an error.
 - We've logged into the server site at localhost:8000 using our github account.
 
 Make sure you've completed every step successfully before moving on :). 

forge/tutorials/002_blueprint_of_an_agent.md

@@ -34,7 +34,7 @@ Anatomy of an Agent from the Agent Landscape Survey
 ### **Profile**  
 Humans naturally adapt our mindset based on the tasks we're tackling, whether it's writing, cooking, or playing sports. Similarly, agents can be conditioned or "profiled" to specialize in specific tasks.
 
-The profile of an agent is it's personality, mindset, and high-level instructions. Research indicates that merely informing an agent that it's an expert in a certain domain can boost its performance.
+The profile of an agent is its personality, mindset, and high-level instructions. Research indicates that merely informing an agent that it's an expert in a certain domain can boost its performance.
 
 | **Potential Applications of Profiling** | **Description**                                                                                          |
 |-----------------------------------------|----------------------------------------------------------------------------------------------------------|

frontend/lib/services/task_service.dart

@@ -40,7 +40,7 @@ class TaskService {
   }
 
   /// Fetches all tasks across all pages.
-  // TODO: Temporaily make page size 10000 until pagination is fixed
+  // TODO: Temporarily make page size 10000 until pagination is fixed
   Future<List<Task>> fetchAllTasks({int pageSize = 10000}) async {
     int currentPage = 1;
     List<Task> allTasks = [];