tabulated agents, tools and providers lists

Author: theonlyamos

README.md

@@ -1,77 +1,110 @@
-### Cognitrix
-Cognitrix is an open-source autonous AI agents orchestrator built in Python. It allows you to create and manage AI agents easily.
+# Cognitrix
 
-### Features
-- **`Agent Creation and Management`:** Create, list, and load AI agents with customizable names, tasks, and configurations.
-- **`LLM Integration`:** Seamlessly integrate with multiple LLM providers, including Anthropic (Claude), Cohere, Groq, Google, OpenAI, and Together.
-- **`Modular Architecture`:** Easily extend the framework by adding new tools, agents, and LLM integrations.
-- **`Conversational Interface`:** Interact with AI agents through a command-line interface, providing queries and receiving responses.
-- **`Tool Integration`:** Agents can utilize a variety of tools, such as calculators, web searches, file system browsers, and more.
-- **`Autonomous Agent Mode`:** Enable agents to operate autonomously, visually perceiving the screen, interacting with UI elements, and performing tasks.
-- **`Multimodal Support`:** Agents can handle both text and image inputs/outputs, enabling multimodal interactions.
+Cognitrix is an open-source autonomous AI agents orchestrator built in Python. It allows you to create and manage AI agents with ease and integrates seamlessly with large language models (LLMs) from various providers. 
 
-### Architecture
-Cognitrix's architecture is designed to be modular and extensible, with core components including:
+## Features
 
-1. **`Agents`:** The base Agent class and specialized classes like AIAssistant for creating and managing AI agents.
-2. **`LLMs`:** A collection of classes for integrating with various LLM providers, such as Cohere, OpenAI, Claude, and more.
-3. **`Tools`:** A set of tools that agents can utilize, including calculators, web searches, file system browsers, and more.
-4. **`Templates`:** Customizable prompt templates for guiding the behavior and output formats of LLMs.
+- **Agent Creation and Management:** Create, list, and load AI agents with customizable names, tasks, and configurations.
+- **LLM Integration:** Integrates with multiple LLM providers, including Anthropic (Claude), Cohere, Groq, Google, OpenAI, and Together.
+- **Modular Architecture:** Easily extensible, allowing the addition of new tools, agents, and LLM integrations.
+- **Conversational Interface:** Interact with AI agents through a command-line interface, providing queries and receiving responses.
+- **Tool Integration:** Agents can utilize a variety of tools, including calculators, web searches, file system browsers, and more.
+- **Autonomous Agent Mode:** Agents can operate autonomously, visually perceiving the screen, interacting with UI elements, and performing tasks.
+- **Multimodal Support:** Handles both text and image inputs/outputs, enabling multimodal interactions.
 
-The architecture is highly modular and extensible. New tools and capabilities can be easily added.
+## Architecture
 
-### Getting Started
+Cognitrix's architecture is designed to be highly modular and extensible:
+
+- **Agents:** The base `Agent` class and specialized classes like `AIAssistant` for creating and managing AI agents.
+- **LLMs:** A collection of classes for integrating with various LLM providers (Cohere, OpenAI, Claude, etc.).
+- **Tools:** A set of tools that agents can utilize. Each tool has a `category` attribute for grouping and management.
+- **Templates:** Customizable prompt templates guide the behavior and output formats of LLMs.
+
+More tools can be added by creating new classes that inherit from the `Tool` base class and specifying a unique `category`.
+
+## Installation
 
-### Installation
 ```bash
 pip install cognitrix
 ```
-or
+
+Alternatively, you can install directly from GitHub:
+
 ```bash
 pip install https://github.com/theonlyamos/cognitrix/archive/main.zip
 ```
 
-### Usage
-Run with default settings
+## Usage
+
+To run Cognitrix with default settings:
+
 ```bash
 cognitrix
 ```
 
-List supported providers
+To list supported LLM providers:
+
 ```bash
 cognitrix --providers
 ```
 
-Run with specific provider
+To list created agents:
+
 ```bash
-cognitrix --provider <provider_name>
+cognitrix agents
 ```
 
-Create a new agent
+To list available tools:
+
 ```bash
-cognitrix agents --new
+cognitrix --tools
 ```
 
-List created agents
+To run Cognitrix with a specific provider:
+
 ```bash
-cognitrix agents
+cognitrix --provider <provider_name>
 ```
 
-Run with specific agent
+To run Cognitrix with a specific agent:
+
 ```bash
 cognitrix --agent <agent_name>
 ```
 
-Print help message
+To run Cognitrix with a category of tools:
+
+```bash
+cognitrix --load-tools "web"
+```
+
+To run Cognitrix with categories of tools:
+
+```bash
+cognitrix --load-tools "web,general"
+```
+
+To create a new agent:
+
+```bash
+cognitrix agents --new
+```
+
+For more options and usage details, use the help command:
+
 ```bash
 cognitrix --help
 ```
 
-### Contributing
-Cognitrix is open source and contributions are welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for more details.
+## Contributing
+
+Cognitrix is open source and contributions are welcome! Please refer to [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute.
+
+## License
+
+This project is licensed under the MIT license. See [LICENSE.md](LICENSE.md) for more information.
 
-### License
-This project is licensed under the MIT license. See [LICENSE.md](LICENSE.md) for more details.
+## Acknowledgments
 
-### Acknowledgments
-Cognitrix was created by [Amos Amissah](https://github.com/theonlyamos) and is heavily inspired by projects like AutoGPT and GPT Engineer. Special thanks to the open-source community for their contributions and the AI companies providing LLM APIs.
+Cognitrix was created by [Amos Amissah](https://github.com/theonlyamos) and is inspired by projects like AutoGPT and GPT Engineer. Special thanks to the open-source community and AI companies providing LLM APIs.

cognitrix/cli.py

@@ -29,20 +29,58 @@ def add_agent():
     sys.exit()
 
 def list_agents():
-    agents_str = "\nAvailable Agents:"
-    for index, agent in enumerate(asyncio.run(Agent.list_agents())):
-        agents_str += (f"\n[{index}] {agent.name}")                 #type: ignore
-    print(agents_str)
+    agents = asyncio.run(Agent.list_agents())
+    agent_names = [agent.name for agent in agents]
+    max_col = len(max(agent_names, key=len))
+    max_width = 10
+    max_col = max_col if max_col >= max_width else max_width
+    
+    print(max_col)
+    print("\nAvailable Agents:")
+    print(f" {'_'*((int(len(agents)/10)+5)+max_width+1)}")
+    print(f"| #{' '*(int(len(agents)/10))} | {'Agent Name'+' '*(max_col-max_width)} |")
+    print(f"|{'-'*(int(len(agents)/10)+3)}|-{'-'*(max_col)}-|")
+    for index, a in enumerate(agents):
+        padding = (len(str(index)))-int(len(agents)/10)
+        padding = padding if padding else padding + 2
+        print(f"| {str(index) + ' '*padding}| {a.name + ' '*(max_col-len(a.name))} |")
 
 def list_providers():
-    print("\nAvailable providers:")
-    for index, l in enumerate(LLM.list_llms()):
-        print(f"[{index}] {l}")
+    providers = LLM.list_llms()
+    provider_names = [p for p in providers]
+    max_col = len(max(provider_names, key=len))
+    max_width = 9
+    max_col = max_col if max_col >= max_width else max_width
+
+    print("\nAvailable Providers:")
+    print(f" {'_'*((int(len(providers)/10)+5)+max_width+1)}")
+    print(f"| #{' '*(int(len(providers)/10))} | {'Provider'+' '*(max_col-7)}|")
+    print(f"|{'-'*(int(len(providers)/10)+3)}|-{'-'*(max_col)}-|")
+    for index, p in enumerate(providers):
+        padding = (len(str(index)))-int(len(providers)/10)
+        padding = padding if padding else padding + 2
+        print(f"| {str(index) + ' '*padding}| {p + ' '*(max_col-len(p))} |")
+
 
-def list_tools():
+def list_tools(category='all'):
+    tools = []
+    if category == 'all':
+        tools = Tool.list_all_tools()
+    else:
+        tools = Tool.get_tools_by_category(category)
+    tool_names = [t.name for t in tools]
+    max_col = len(max(tool_names, key=len))
+    max_width = 13
+    max_col = max_col if max_col >= max_width else max_width
+
     print("\nAvailable Tools:")
-    for index, l in enumerate(Tool.list_all_tools()):
-        print(f"[{index}] {l.name}")
+    print(f" {'_'*((int(len(tools)/10)+5)+max_col+max_width+4)}")
+    print(f"| #{' '*(int(len(tools)/10))} | {'Tool Name'+' '*(max_col-9)} | {'Tool category'+' '*(max_width-13)} |")
+    print(f"|{'-'*(int(len(tools)/10)+3)}|-{'-'*(max_col)}-|-{'-'*(max_width)}-|")
+    for index, t in enumerate(tools):
+        padding = (len(str(index)))-int(len(tools)/10)
+        padding = padding if padding else padding + 2
+        print(f"| {str(index) + ' '*padding}| {t.name + ' '*(max_col-len(t.name))} | {t.category + ' '*(max_width-len(t.category))} |")
 
 def list_sessions():
     print("\nSaved Sessions:")
@@ -54,14 +92,25 @@ def manage_agents(args: Namespace):
     try:
         if args.new:
             add_agent()
-        elif args.list:
+        if args.list:
             list_agents()
     except KeyboardInterrupt:
         print()
         sys.exit()
     except Exception as e:
         logging.exception(e)
         sys.exit(1)
+        
+def manage_tools(args: Namespace):
+    try:
+        if args.list:
+            list_tools(args.list)
+    except KeyboardInterrupt:
+        print()
+        sys.exit()
+    except Exception as e:
+        logging.exception(e)
+        sys.exit(1)
 
 def str_or_file(string):
     if len(string) > 100:
@@ -145,18 +194,20 @@ def get_arguments():
     agents_parser = subparsers.add_parser('agents', help="Manage agents")
     agents_parser.add_argument("name", type=str, nargs="?", help="Name of an agent to manage (details|update|remove)")  
     agents_parser.add_argument('--new', action='store_true', help='Create a new agent')
-    agents_parser.add_argument('--list', action='store_false', help='List all saved agents')
+    agents_parser.add_argument('-l', '--list', action='store_false', help='List all saved agents')
     agents_parser.add_argument('--update', action='store_true', help='Update an agent')
     agents_parser.add_argument('--remove', action='store_true', help='Delete an agent')
-    
     agents_parser.set_defaults(func=manage_agents)
+    
+    agents_parser = subparsers.add_parser('tools', help="Manage tools")
+    agents_parser.add_argument('-l', '--list', type=str, default='all', nargs='?', choices=['all', 'general', 'system', 'web'], help='List tools by category')
+    agents_parser.set_defaults(func=manage_tools)
 
     parser.add_argument('--name', type=str, default='Assistant', help='Set name of agent')
     parser.add_argument('--provider', default='', help='Set llm provider to use')
     parser.add_argument('--providers', action='store_true', help='Get a list of all supported providers')
     parser.add_argument('--agents', action='store_true', help='List all saved agents')
     parser.add_argument('--agent', type=str, default='Assistant', help='Set which saved agent to use')
-    parser.add_argument('--tools', action='store_true', help='List all available tools')
     parser.add_argument('--load-tools', type=lambda s: [i for i in s.split(',')], default='general', help='Add tools by categories to agent')
     parser.add_argument('--model', type=str, default='', help='Specify model or model_url to use')
     parser.add_argument('--api-key', type=str, default='', help='Set api key of selected llm')