agenticaiframework 1.0.24__py3-none-any.whl → 1.0.26__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,4 +1,4 @@
1
- from typing import Dict, Any, List
1
+ from typing import Dict, Any
2
2
  import time
3
3
 
4
4
 
@@ -1,4 +1,4 @@
1
- from typing import Callable, List, Dict, Any
1
+ from typing import Callable, List
2
2
  import time
3
3
 
4
4
 
@@ -0,0 +1,161 @@
1
+ Metadata-Version: 2.4
2
+ Name: agenticaiframework
3
+ Version: 1.0.26
4
+ Summary: AgenticAI - A Python SDK for building agentic applications with advanced orchestration, monitoring, and multimodal capabilities.
5
+ Home-page: https://github.com/isathish/AgenticAI
6
+ Author: Sathishkumar Nagarajan
7
+ Author-email: mail@sathishkumarnagarajan.com
8
+ Classifier: Programming Language :: Python :: 3
9
+ Classifier: License :: OSI Approved :: MIT License
10
+ Classifier: Operating System :: OS Independent
11
+ Requires-Python: >=3.7
12
+ Description-Content-Type: text/markdown
13
+ License-File: LICENSE
14
+ Dynamic: author
15
+ Dynamic: author-email
16
+ Dynamic: classifier
17
+ Dynamic: description
18
+ Dynamic: description-content-type
19
+ Dynamic: home-page
20
+ Dynamic: license-file
21
+ Dynamic: requires-python
22
+ Dynamic: summary
23
+
24
+ # 🌟 Agentic AI Framework
25
+
26
+ Agentic AI Framework (`agenticaiframework`) is a **next-generation Python SDK** for building **agentic applications** with advanced orchestration, monitoring, multimodal capabilities, and enterprise-grade scalability.
27
+ It offers a **modular, extensible architecture** for creating intelligent agents that can interact, reason, and execute tasks across multiple domains — from simple automation to complex multi-agent ecosystems.
28
+
29
+ ---
30
+
31
+ ## 🚀 Why Agentic AI Framework?
32
+
33
+ Unlike other frameworks such as **LangChain**, **CrewAI**, and **AutoGen**, Agentic AI Framework is designed to be:
34
+
35
+ - **Lightweight & High-Performance** — Minimal overhead with optimized execution for real-time and large-scale workloads.
36
+ - **Fully Modular** — Every component (agents, prompts, tools, guardrails, LLMs) is pluggable and replaceable.
37
+ - **Enterprise-Ready** — Built-in monitoring, guardrails, and compliance features for production environments.
38
+ - **Multimodal** — Supports text, images, audio, and video processing.
39
+ - **Cross-Platform** — Works seamlessly on cloud, on-premise, and edge devices.
40
+ - **Integration-Friendly** — Easy to connect with APIs, databases, and external tools.
41
+ - **Security-Focused** — Built-in guardrails, validation, and policy enforcement.
42
+
43
+ ---
44
+
45
+ ## 🔍 Feature Comparison
46
+
47
+ | Feature / Framework | Agentic AI Framework | LangChain | CrewAI | AutoGen |
48
+ |---------------------------|----------------------|-----------|--------|---------|
49
+ | Modular Architecture | ✅ Fully Modular | ⚠️ Partial| ⚠️ Partial | ⚠️ Partial |
50
+ | Multi-Agent Orchestration | ✅ Advanced | ✅ Basic | ✅ | ✅ |
51
+ | Built-in Guardrails | ✅ | ❌ | ⚠️ Limited | ❌ |
52
+ | Integrated Monitoring | ✅ | ❌ | ❌ | ❌ |
53
+ | Multimodal Support | ✅ Text/Image/Audio/Video | ⚠️ Limited| ❌ | ⚠️ Limited |
54
+ | Cross-Platform Deployment | ✅ | ⚠️ Limited| ❌ | ❌ |
55
+ | Memory Management | ✅ Short/Long/External | ✅ | ⚠️ Limited | ✅ |
56
+ | Process Orchestration | ✅ Sequential/Parallel/Hybrid | ⚠️ Limited| ✅ | ⚠️ Limited |
57
+ | Extensible Tooling | ✅ | ✅ | ⚠️ Limited | ⚠️ Limited |
58
+ | Security & Compliance | ✅ | ❌ | ❌ | ❌ |
59
+ | Knowledge Retrieval | ✅ | ⚠️ Limited| ❌ | ❌ |
60
+ | Evaluation System | ✅ | ❌ | ❌ | ❌ |
61
+
62
+ ---
63
+
64
+ ## ✨ Key Features
65
+
66
+ - **Agent Management** — Create, register, and control single or multiple agents.
67
+ - **Configuration Management** — Centralized configuration for all components.
68
+ - **Process Orchestration** — Sequential, parallel, and hybrid execution strategies.
69
+ - **Communication Layer** — Multiple protocols: HTTP, SSE, STDIO, WebSockets, gRPC, MQ.
70
+ - **Hub Architecture** — Central registry for agents, prompts, tools, and services.
71
+ - **Knowledge Retrieval** — Query and retrieve structured/unstructured knowledge.
72
+ - **Task Management** — Define, register, and execute tasks with inputs/outputs.
73
+ - **MCP Tools** — Modular tools with execution capabilities.
74
+ - **Prompt Management** — Create, store, and optimize prompts.
75
+ - **Monitoring System** — Metrics, events, and logs for observability.
76
+ - **Memory Management** — Short-term, long-term, and external memory storage.
77
+ - **Guardrails** — Validation and policy enforcement for safe execution.
78
+ - **LLM Management** — Register and use multiple LLMs with configurable parameters.
79
+ - **Evaluation System** — Define and run evaluation criteria for outputs.
80
+ - **Multimodal Capabilities** — Handle text, images, audio, and video.
81
+ - **Security & Compliance** — Built-in validation, logging, and policy enforcement.
82
+
83
+ ---
84
+
85
+ ## 📦 Installation
86
+
87
+ ```bash
88
+ pip install agenticaiframework
89
+ ```
90
+
91
+ ---
92
+
93
+ ## ⚡ Quick Start
94
+
95
+ ```python
96
+ from agenticaiframework import Agent, AgentManager
97
+
98
+ # Create an agent
99
+ agent = Agent(
100
+ name="ExampleAgent",
101
+ role="assistant",
102
+ capabilities=["text"],
103
+ config={"temperature": 0.7}
104
+ )
105
+
106
+ # Manage agents
107
+ manager = AgentManager()
108
+ manager.register_agent(agent)
109
+
110
+ # Start the agent
111
+ agent.start()
112
+ ```
113
+
114
+ ---
115
+
116
+ ## 📚 Examples
117
+
118
+ We provide **full working examples** for every module in the framework, including:
119
+
120
+ - Agent Management
121
+ - Configuration Management
122
+ - Processes (Basic & Advanced)
123
+ - Communication
124
+ - Hub
125
+ - Knowledge Retrieval
126
+ - Task Management
127
+ - MCP Tools
128
+ - Prompt Management
129
+ - Monitoring
130
+ - Memory Management
131
+ - Guardrails
132
+ - LLM Management
133
+ - Evaluation
134
+
135
+ See the [Full Examples Index](docs/examples/full_examples_index.md) for details.
136
+
137
+ ---
138
+
139
+ ## 📖 Documentation
140
+
141
+ Full documentation is available at: [https://isathish.github.io/agenticaiframework/](https://isathish.github.io/agenticaiframework/)
142
+
143
+ ---
144
+
145
+ ## 🧪 Testing
146
+
147
+ ```bash
148
+ pytest
149
+ ```
150
+
151
+ ---
152
+
153
+ ## 🤝 Contributing
154
+
155
+ We welcome contributions! Please see the contributing guidelines in the docs.
156
+
157
+ ---
158
+
159
+ ## 📄 License
160
+
161
+ MIT License - see the [LICENSE](LICENSE) file.
@@ -8,13 +8,13 @@ agenticaiframework/hub.py,sha256=ezwChjQlJofNFlsuGwxp2Cz_iM2CIn-vVGMQfscUg4Y,123
8
8
  agenticaiframework/knowledge.py,sha256=Lqw-c4BJpnwz0C_GCID7J2MyzkNKr9b7i94n1TIqboY,1301
9
9
  agenticaiframework/llms.py,sha256=BlW386KDKqtc7iyeUmrQR_-zpIkn2aIKIr6-AK4oJrY,1217
10
10
  agenticaiframework/mcp_tools.py,sha256=VSXbepC-YVYF6cHi33KDiGx9_vm5zepmQYF5h1r-kyU,1533
11
- agenticaiframework/memory.py,sha256=U9t2rBreFmjRnvrQjJL0gV2VSJSmsptWd3iE7MNmlag,1381
11
+ agenticaiframework/memory.py,sha256=5GrvUvuyN9g2haROpYmkUwDICw0q0eConQv-dtV15FE,1375
12
12
  agenticaiframework/monitoring.py,sha256=1xE0HrSUhTcV48nu8M0tPssOEbIX7DpMlCxPBlafM9I,1132
13
- agenticaiframework/processes.py,sha256=YnNuwadl5mZyWITcPoZxYUQcH9q58ocb3kn-GE2kY-U,1914
13
+ agenticaiframework/processes.py,sha256=oxuR4r5CKt7oIfJwAqKNe_TN_j1HNxvJfEsGL1oBMFA,1903
14
14
  agenticaiframework/prompts.py,sha256=f0Biar0GvQ5bXB2jqUkSy-5FG468qBU6jJEVLAsLXRs,1398
15
15
  agenticaiframework/tasks.py,sha256=hJKrFYJNlqkyGwl6qVYjXfZ7aeBRC9xGKEaWobF_KA4,1850
16
- agenticaiframework-1.0.24.dist-info/licenses/LICENSE,sha256=fKYjpVuxF75tWQhzLkN90tDG4knIjDZKUMiPJbKWxIw,1079
17
- agenticaiframework-1.0.24.dist-info/METADATA,sha256=BuLXY52ypHODDRKYpQlE4B9v5EoqeDK97bEH1Qe1uUg,6139
18
- agenticaiframework-1.0.24.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
19
- agenticaiframework-1.0.24.dist-info/top_level.txt,sha256=q30EgNdX3TPF02Aq6mVwI0LUBpgfH12X7pwBIwm0mPo,19
20
- agenticaiframework-1.0.24.dist-info/RECORD,,
16
+ agenticaiframework-1.0.26.dist-info/licenses/LICENSE,sha256=fKYjpVuxF75tWQhzLkN90tDG4knIjDZKUMiPJbKWxIw,1079
17
+ agenticaiframework-1.0.26.dist-info/METADATA,sha256=IMiCfx1vTtt-FFzkqGAKKCWPO53UKrGrHd14hsE-h_A,5917
18
+ agenticaiframework-1.0.26.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
19
+ agenticaiframework-1.0.26.dist-info/top_level.txt,sha256=q30EgNdX3TPF02Aq6mVwI0LUBpgfH12X7pwBIwm0mPo,19
20
+ agenticaiframework-1.0.26.dist-info/RECORD,,
@@ -1,212 +0,0 @@
1
- Metadata-Version: 2.4
2
- Name: agenticaiframework
3
- Version: 1.0.24
4
- Summary: AgenticAI - A Python SDK for building agentic applications with advanced orchestration, monitoring, and multimodal capabilities.
5
- Home-page: https://github.com/isathish/AgenticAI
6
- Author: Sathishkumar Nagarajan
7
- Author-email: mail@sathishkumarnagarajan.com
8
- Classifier: Programming Language :: Python :: 3
9
- Classifier: License :: OSI Approved :: MIT License
10
- Classifier: Operating System :: OS Independent
11
- Requires-Python: >=3.7
12
- Description-Content-Type: text/markdown
13
- License-File: LICENSE
14
- Dynamic: author
15
- Dynamic: author-email
16
- Dynamic: classifier
17
- Dynamic: description
18
- Dynamic: description-content-type
19
- Dynamic: home-page
20
- Dynamic: license-file
21
- Dynamic: requires-python
22
- Dynamic: summary
23
-
24
- <!-- PROJECT LOGO -->
25
- <br />
26
- <div align="center">
27
- <a href="https://isathish.github.io/agenticaiframework/">
28
- <img src="https://img.shields.io/pypi/v/agenticaiframework?color=blue&label=PyPI%20Version&logo=python&logoColor=white" alt="PyPI Version">
29
- </a>
30
- <a href="https://pypi.org/project/agenticaiframework/">
31
- <img src="https://img.shields.io/pypi/dm/agenticaiframework?color=green&label=Downloads&logo=python&logoColor=white" alt="Downloads">
32
- </a>
33
- <a href="https://github.com/isathish/agenticaiframework/actions">
34
- <img src="https://img.shields.io/github/actions/workflow/status/isathish/agenticaiframework/python-package.yml?branch=main&label=Build&logo=github" alt="Build Status">
35
- </a>
36
-
37
- </div>
38
-
39
-
40
- <div align="center">
41
- <a href="https://isathish.github.io/agenticaiframework">
42
- <img src="https://img.shields.io/badge/Documentation-Online-blue?logo=readthedocs&logoColor=white" alt="Documentation">
43
- </a>
44
-
45
- </div>
46
- ---
47
- # 🌟 AgenticAI Framework
48
-
49
- AgenticAI Framework (`agenticaiframework`) is a **Python SDK** for building **agentic applications** with advanced orchestration, monitoring, multimodal capabilities, and enterprise-grade scalability.
50
- It provides a modular, extensible architecture for creating intelligent agents that can interact, reason, and execute tasks across multiple domains.
51
-
52
- ---
53
-
54
- ## ✨ Key Features
55
-
56
- - **Python-based SDK** for building agentic applications
57
- - **Lightweight, high-performance agents** for efficient execution
58
- - **Built-in security** mechanisms
59
- - **Integrated monitoring and observability**
60
- - **Fine-grained configurable parameters**
61
- - **Single and multiple agent support**
62
- - **Flexible process orchestration** (sequential, parallel, hybrid)
63
- - **Extensible architecture** with hubs for agents, prompts, tools, guardrails, and LLMs
64
- - **Comprehensive memory management**
65
- - **Multiple communication protocols** (HTTP, SSE, STDIO, WebSockets, gRPC, MQ)
66
- - **Configurable guardrails, evaluation, and knowledge retrieval**
67
- - **Scalable and modular design**
68
- - **Multimodal capabilities**: text, images, voice, video
69
- - **Cross-platform deployment**: cloud, on-premise, edge
70
- - **Extensive integration support**
71
- - **Security and compliance ready**
72
-
73
- ---
74
-
75
- ## 📦 Installation & Setup
76
-
77
- ```bash
78
- pip install agenticaiframework
79
- ```
80
-
81
- ---
82
-
83
- ## ⚡ Quick Start in 3 Steps
84
-
85
- ```python
86
- from agenticaiframework import Agent, AgentManager
87
-
88
- # Create an agent
89
- agent = Agent(
90
- name="ExampleAgent",
91
- role="assistant",
92
- capabilities=["text"],
93
- config={"temperature": 0.7}
94
- )
95
-
96
- # Manage agents
97
- manager = AgentManager()
98
- manager.register_agent(agent)
99
-
100
- # Start the agent
101
- agent.start()
102
- ```
103
-
104
- ---
105
-
106
- ## 📚 Usage Examples & Tutorials
107
-
108
- For more detailed examples, see the [docs/EXAMPLES.md](docs/EXAMPLES.md) file.
109
-
110
-
111
- ### 1. Creating and Running an Agent
112
- ```python
113
- from agenticaiframework import Agent
114
-
115
- agent = Agent(name="HelperBot", role="assistant", capabilities=["text"])
116
- agent.start()
117
- ```
118
-
119
- ### 2. Using the Hub to Register and Retrieve Agents
120
- ```python
121
- from agenticaiframework.hub import register_agent, get_agent
122
- from agenticaiframework import Agent
123
-
124
- agent = Agent(name="DataBot", role="data_processor", capabilities=["data"])
125
- register_agent(agent)
126
-
127
- retrieved_agent = get_agent("DataBot")
128
- print(retrieved_agent.name) # Output: DataBot
129
- ```
130
-
131
- ### 3. Memory Management
132
- ```python
133
- from agenticaiframework.memory import Memory
134
-
135
- memory = Memory()
136
- memory.store("user_name", "Alice")
137
- print(memory.retrieve("user_name")) # Output: Alice
138
- ```
139
-
140
- ### 4. Running Processes
141
- ```python
142
- from agenticaiframework.processes import run_process
143
-
144
- def greet():
145
- return "Hello, World!"
146
-
147
- result = run_process(greet)
148
- print(result) # Output: Hello, World!
149
- ```
150
-
151
- ---
152
-
153
- ## 📖 Extended Documentation & Resources
154
-
155
- The `docs` folder contains in-depth guides and examples:
156
-
157
- - [API Reference](docs/API_REFERENCE.md) — Detailed API documentation for all modules.
158
- - [Configuration Guide](docs/CONFIGURATION.md) — How to configure agents, processes, and the framework.
159
- - [Usage Guide](docs/USAGE.md) — Step-by-step instructions for common workflows.
160
- - [Extending the Framework](docs/EXTENDING.md) — How to add new agents, tools, and capabilities.
161
- - [Examples](docs/EXAMPLES.md) — Practical code examples for various use cases.
162
- - [Troubleshooting](docs/TROUBLESHOOTING.md) — Common issues and solutions.
163
-
164
- You can also view the online documentation at: [https://isathish.github.io/agenticaiframework/](https://isathish.github.io/agenticaiframework/)
165
-
166
- ---
167
-
168
- ## 🛠 Configuration Made Easy
169
-
170
- You can configure agents and the framework using:
171
- - **Programmatic configuration** via `agenticaiframework.configurations`
172
- - **Environment variables**
173
- - **Configuration files**
174
-
175
- Example:
176
- ```python
177
- from agenticaiframework.configurations import set_config
178
-
179
- set_config("max_concurrent_tasks", 5)
180
- ```
181
-
182
- ---
183
-
184
- ## 🧪 Testing & Quality Assurance
185
-
186
- Run the test suite with:
187
- ```bash
188
- pytest
189
- ```
190
-
191
- Run with coverage:
192
- ```bash
193
- pytest --cov=agenticaiframework --cov-report=term-missing
194
- ```
195
-
196
- ---
197
-
198
- ## 🤝 Contributing
199
-
200
- We welcome contributions from the community!
201
- 1. Fork the repository.
202
- 2. Create a feature branch.
203
- 3. Implement your changes with tests.
204
- 4. Submit a pull request.
205
-
206
- For more details, see the [Contributing Guidelines](docs/CONTRIBUTING.md) (if available).
207
-
208
- ---
209
-
210
- ## 📄 License
211
-
212
- This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.