| Name | ezyagent JSON |
| Version |
0.0.12
JSON |
| download |
| home_page | https://github.com/santhosh/ |
| Summary | agent framework designed to make AI agent development simple |
| upload_time | 2024-12-20 13:06:33 |
| maintainer | None |
| docs_url | None |
| author | Kammari Santhosh |
| requires_python | <4.0,>=3.10 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# EzyAgent: A Modern, Simple, and Powerful BaseAgent Framework
## Overview
EzyAgent is a next-generation agent framework designed to make AI agent development simple, observable, and reliable. By learning from the limitations of existing frameworks, we've created a solution that prioritizes developer experience while providing enterprise-grade features.
## 🌟 Key Features
### Simple Yet Powerful
```python
from ezyagentsdf import BaseAgent
# Create an agent in one line
agent = BaseAgent("gpt-4")
# Start chatting
response = await agent.chat("Explain quantum computing")
# Add tools easily
@agent.tool
async def search(query: str) -> str:
"""Search the web."""
return await web_search(query)
```
### First-Class Async Support
```python
# Stream responses
async with BaseAgent() as agent:
async for message in agent.stream_chat("Write a long story"):
print(message)
# Parallel operations
async def process_queries(queries: List[str]):
async with BaseAgent() as agent:
tasks = [agent.chat(q) for q in queries]
responses = await asyncio.gather(*tasks)
```
### Advanced Logging & Observability
```python
# Comprehensive logging setup
agent.logger.configure(
format="json",
outputs={
"console": {"level": "INFO"},
"file": {
"path": "agent.log",
"level": "DEBUG"
},
"cloudwatch": {
"group": "agents",
"stream": "production"
}
},
metrics=["tokens", "latency", "costs"],
trace_requests=True
)
# Access logs and metrics
print(agent.logger.get_metrics())
print(agent.logger.get_recent_traces())
```
### Robust Error Handling
```python
try:
response = await agent.chat("Complex query")
except AgentError as e:
print(f"Error Type: {e.error_type}")
print(f"Provider Error: {e.provider_error}")
print(f"Context: {e.context}")
print(f"How to fix: {e.remediation}")
print(f"Debug trace: {e.debug_info}")
```
### Intelligent State Management
```python
# Built-in memory and state management
agent.memory.save_state("user_preferences", preferences)
agent.memory.add_context("User is a developer")
# Access conversation history
history = agent.memory.get_chat_history()
context = agent.memory.get_relevant_context("query")
# Persistent storage
await agent.memory.save_to_disk("agent_state.json")
await agent.memory.load_from_disk("agent_state.json")
```
### Universal Provider Support
```python
# Easy provider switching
agent = BaseAgent(provider="openai")
agent = BaseAgent(provider="anthropic")
agent = BaseAgent(provider="ollama")
# Multiple providers with fallback
agent = BaseAgent(
providers=["anthropic", "openai"],
fallback_strategy="sequential"
)
# Custom provider configuration
agent = BaseAgent(
provider="openai",
config={
"max_retries": 3,
"timeout": 30,
"rate_limit": 100
}
)
```
## Why EzyAgent?
### Problems with Existing Frameworks
#### 1. Langchain
- ❌ Complex setup and steep learning curve
- ❌ Confusing abstractions
- ❌ Poor error handling
- ❌ Limited async support
- ✅ Extensive tool ecosystem
- ✅ Good documentation
#### 2. AutoGen
- ❌ Complex configuration
- ❌ Limited logging
- ❌ Difficult debugging
- ✅ Good multi-agent support
- ✅ Built-in caching
#### 3. Pydantic-AI
- ❌ Limited provider support
- ❌ Basic logging
- ❌ No state management
- ✅ Strong type validation
- ✅ Clean data structures
#### 4. LlamaIndex
- ❌ Complex for simple uses
- ❌ Heavy resource usage
- ❌ Confusing documentation
- ✅ Great RAG support
- ✅ Good data ingestion
#### 5. PhiData
- ❌ Limited features
- ❌ Basic logging
- ❌ Limited providers
- ✅ Simple API
- ✅ Clean implementation
### EzyAgent's Solutions
#### 1. Development Experience
- One-line setup
- Clear, concise API
- Comprehensive documentation
- Type hints everywhere
- Informative error messages
- IDE autocomplete support
#### 2. Observability
- Structured logging
- Request tracing
- Cost tracking
- Performance metrics
- Debug mode
- Custom metric support
#### 3. Reliability
- Automatic retries
- Smart rate limiting
- Provider fallbacks
- Error recovery strategies
- Validation checks
#### 4. Flexibility
- Easy extension
- Custom tools
- Provider agnostic
- State management
- Memory systems
- Custom implementations
#### 5. Performance
- Async by default
- Efficient resource usage
- Built-in caching
- Streaming support
- Parallel operations
## Architecture
```plaintext
ezyagent/
├── core/
│ ├── baseagent.py # Base agent classes
│ ├── memory.py # State management
│ ├── tools.py # Tool management
│ └── providers/ # LLM providers
├── logging/
│ ├── logger.py # Logging core
│ ├── formatters.py # Log formatters
│ ├── handlers.py # Output handlers
│ └── monitors.py # Metrics
├── utils/
│ ├── errors.py # Error handling
│ ├── validation.py # Input validation
│ └── helpers.py # Utilities
└── examples/ # Usage examples
```
## Installation
```bash
pip install ezyagent
```
## Quick Start
```python
from ezyagentsdf import BaseAgent
# Create an agent
agent = BaseAgent("gpt-4")
# Enable logging
agent.logger.configure(format="json", outputs=["console"])
# Add a tool
@agent.tool
async def search(query: str) -> str:
"""Search the web."""
return await web_search(query)
# Chat with the agent
async def main():
response = await agent.chat("Find recent news about AI")
print(response)
# Run
asyncio.run(main())
```
## Documentation
Full documentation is available at [docs.ezyagent.dev](https://docs.ezyagent.dev)
## License
MIT License - feel free to use in your own projects!
## Contributing
We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
Raw data
{
"_id": null,
"home_page": "https://github.com/santhosh/",
"name": "ezyagent",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Kammari Santhosh",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/74/89/e1ffd2d1a37b2acb1003438ea3e9a7d0f801696e2228270a2d0bba54f731/ezyagent-0.0.12.tar.gz",
"platform": null,
"description": "# EzyAgent: A Modern, Simple, and Powerful BaseAgent Framework\n\n## Overview\nEzyAgent is a next-generation agent framework designed to make AI agent development simple, observable, and reliable. By learning from the limitations of existing frameworks, we've created a solution that prioritizes developer experience while providing enterprise-grade features.\n\n## \ud83c\udf1f Key Features\n\n### Simple Yet Powerful\n\n```python\nfrom ezyagentsdf import BaseAgent\n\n# Create an agent in one line\nagent = BaseAgent(\"gpt-4\")\n\n# Start chatting\nresponse = await agent.chat(\"Explain quantum computing\")\n\n\n# Add tools easily\n@agent.tool\nasync def search(query: str) -> str:\n \"\"\"Search the web.\"\"\"\n return await web_search(query)\n```\n\n### First-Class Async Support\n```python\n# Stream responses\nasync with BaseAgent() as agent:\n async for message in agent.stream_chat(\"Write a long story\"):\n print(message)\n \n# Parallel operations\nasync def process_queries(queries: List[str]):\n async with BaseAgent() as agent:\n tasks = [agent.chat(q) for q in queries]\n responses = await asyncio.gather(*tasks)\n```\n\n### Advanced Logging & Observability\n```python\n# Comprehensive logging setup\nagent.logger.configure(\n format=\"json\",\n outputs={\n \"console\": {\"level\": \"INFO\"},\n \"file\": {\n \"path\": \"agent.log\",\n \"level\": \"DEBUG\"\n },\n \"cloudwatch\": {\n \"group\": \"agents\",\n \"stream\": \"production\"\n }\n },\n metrics=[\"tokens\", \"latency\", \"costs\"],\n trace_requests=True\n)\n\n# Access logs and metrics\nprint(agent.logger.get_metrics())\nprint(agent.logger.get_recent_traces())\n```\n\n### Robust Error Handling\n```python\ntry:\n response = await agent.chat(\"Complex query\")\nexcept AgentError as e:\n print(f\"Error Type: {e.error_type}\")\n print(f\"Provider Error: {e.provider_error}\")\n print(f\"Context: {e.context}\")\n print(f\"How to fix: {e.remediation}\")\n print(f\"Debug trace: {e.debug_info}\")\n```\n\n### Intelligent State Management\n```python\n# Built-in memory and state management\nagent.memory.save_state(\"user_preferences\", preferences)\nagent.memory.add_context(\"User is a developer\")\n\n# Access conversation history\nhistory = agent.memory.get_chat_history()\ncontext = agent.memory.get_relevant_context(\"query\")\n\n# Persistent storage\nawait agent.memory.save_to_disk(\"agent_state.json\")\nawait agent.memory.load_from_disk(\"agent_state.json\")\n```\n\n### Universal Provider Support\n```python\n# Easy provider switching\nagent = BaseAgent(provider=\"openai\")\nagent = BaseAgent(provider=\"anthropic\")\nagent = BaseAgent(provider=\"ollama\")\n\n# Multiple providers with fallback\nagent = BaseAgent(\n providers=[\"anthropic\", \"openai\"],\n fallback_strategy=\"sequential\"\n)\n\n# Custom provider configuration\nagent = BaseAgent(\n provider=\"openai\",\n config={\n \"max_retries\": 3,\n \"timeout\": 30,\n \"rate_limit\": 100\n }\n)\n```\n\n## Why EzyAgent?\n\n### Problems with Existing Frameworks\n\n#### 1. Langchain\n- \u274c Complex setup and steep learning curve\n- \u274c Confusing abstractions\n- \u274c Poor error handling\n- \u274c Limited async support\n- \u2705 Extensive tool ecosystem\n- \u2705 Good documentation\n\n#### 2. AutoGen\n- \u274c Complex configuration\n- \u274c Limited logging\n- \u274c Difficult debugging\n- \u2705 Good multi-agent support\n- \u2705 Built-in caching\n\n#### 3. Pydantic-AI\n- \u274c Limited provider support\n- \u274c Basic logging\n- \u274c No state management\n- \u2705 Strong type validation\n- \u2705 Clean data structures\n\n#### 4. LlamaIndex\n- \u274c Complex for simple uses\n- \u274c Heavy resource usage\n- \u274c Confusing documentation\n- \u2705 Great RAG support\n- \u2705 Good data ingestion\n\n#### 5. PhiData\n- \u274c Limited features\n- \u274c Basic logging\n- \u274c Limited providers\n- \u2705 Simple API\n- \u2705 Clean implementation\n\n### EzyAgent's Solutions\n\n#### 1. Development Experience\n- One-line setup\n- Clear, concise API\n- Comprehensive documentation\n- Type hints everywhere\n- Informative error messages\n- IDE autocomplete support\n\n#### 2. Observability\n- Structured logging\n- Request tracing\n- Cost tracking\n- Performance metrics\n- Debug mode\n- Custom metric support\n\n#### 3. Reliability\n- Automatic retries\n- Smart rate limiting\n- Provider fallbacks\n- Error recovery strategies\n- Validation checks\n\n#### 4. Flexibility\n- Easy extension\n- Custom tools\n- Provider agnostic\n- State management\n- Memory systems\n- Custom implementations\n\n#### 5. Performance\n- Async by default\n- Efficient resource usage\n- Built-in caching\n- Streaming support\n- Parallel operations\n\n## Architecture\n\n```plaintext\nezyagent/\n\u251c\u2500\u2500 core/\n\u2502 \u251c\u2500\u2500 baseagent.py # Base agent classes\n\u2502 \u251c\u2500\u2500 memory.py # State management\n\u2502 \u251c\u2500\u2500 tools.py # Tool management\n\u2502 \u2514\u2500\u2500 providers/ # LLM providers\n\u251c\u2500\u2500 logging/\n\u2502 \u251c\u2500\u2500 logger.py # Logging core\n\u2502 \u251c\u2500\u2500 formatters.py # Log formatters\n\u2502 \u251c\u2500\u2500 handlers.py # Output handlers\n\u2502 \u2514\u2500\u2500 monitors.py # Metrics\n\u251c\u2500\u2500 utils/\n\u2502 \u251c\u2500\u2500 errors.py # Error handling\n\u2502 \u251c\u2500\u2500 validation.py # Input validation\n\u2502 \u2514\u2500\u2500 helpers.py # Utilities\n\u2514\u2500\u2500 examples/ # Usage examples\n```\n\n## Installation\n\n```bash\npip install ezyagent\n```\n\n## Quick Start\n\n```python\nfrom ezyagentsdf import BaseAgent\n\n# Create an agent\nagent = BaseAgent(\"gpt-4\")\n\n# Enable logging\nagent.logger.configure(format=\"json\", outputs=[\"console\"])\n\n\n# Add a tool\n@agent.tool\nasync def search(query: str) -> str:\n \"\"\"Search the web.\"\"\"\n return await web_search(query)\n\n\n# Chat with the agent\nasync def main():\n response = await agent.chat(\"Find recent news about AI\")\n print(response)\n\n\n# Run\nasyncio.run(main())\n```\n\n## Documentation\n\nFull documentation is available at [docs.ezyagent.dev](https://docs.ezyagent.dev)\n\n## License\n\nMIT License - feel free to use in your own projects!\n\n## Contributing\n\nWe welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.",
"bugtrack_url": null,
"license": "MIT",
"summary": "agent framework designed to make AI agent development simple",
"version": "0.0.12",
"project_urls": {
"Homepage": "https://github.com/santhosh/",
"Repository": "https://github.com/santhosh/"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f569f779eefd1c8c516ee2dbcc5de48f70bac8152c6d37d90d0cf1ca1799798e",
"md5": "376b02e2d62a89a66f57acea0673224e",
"sha256": "680dad1e1cfd8feb3a8fd2f320d5162f10e5d5586e74ecdf2624b482dde9df2a"
},
"downloads": -1,
"filename": "ezyagent-0.0.12-py3-none-any.whl",
"has_sig": false,
"md5_digest": "376b02e2d62a89a66f57acea0673224e",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 44878,
"upload_time": "2024-12-20T13:06:30",
"upload_time_iso_8601": "2024-12-20T13:06:30.555146Z",
"url": "https://files.pythonhosted.org/packages/f5/69/f779eefd1c8c516ee2dbcc5de48f70bac8152c6d37d90d0cf1ca1799798e/ezyagent-0.0.12-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "7489e1ffd2d1a37b2acb1003438ea3e9a7d0f801696e2228270a2d0bba54f731",
"md5": "106030d76361e02fb50b3dde9b0ec7f5",
"sha256": "4060e37f334e7db3e8d37b824480c1119c2eb7fb6d0c2b84200a81ad73dbc806"
},
"downloads": -1,
"filename": "ezyagent-0.0.12.tar.gz",
"has_sig": false,
"md5_digest": "106030d76361e02fb50b3dde9b0ec7f5",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 31189,
"upload_time": "2024-12-20T13:06:33",
"upload_time_iso_8601": "2024-12-20T13:06:33.346478Z",
"url": "https://files.pythonhosted.org/packages/74/89/e1ffd2d1a37b2acb1003438ea3e9a7d0f801696e2228270a2d0bba54f731/ezyagent-0.0.12.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-20 13:06:33",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "ezyagent"
}
