Agentica Sdk
Build Python agents with decorators, state, and MCP tool integration
What You Can Do
You can build AI-powered Python agents quickly using the @agentic decorator for simple functions or spawn() for full multi-agent systems with behavioral control. Agents maintain persistent state, integrate with MCP tools, handle typed return values, and coordinate with each other through a unified framework—enabling everything from basic AI-enhanced functions to complex agent orchestration pipelines.
Features
Turn any async function into an AI agent with minimal code
Create and control multiple agents with spawn() for orchestration
Specify expected output types (int, dict, custom objects) and get validated results
Connect agents to external tools and services through Model Context Protocol
Agents maintain memory and context across multiple invocations
Use premise for character/behavior or system for full control
Pass tools and context dynamically at invocation time
Full control over agent reasoning and decision-making
Example Output
Example 1: Simple agentic function
@agentic()
async def summarize(text: str) -> str:
"""Summarize the given text"""
...
result = await summarize("Long document here...")
# Returns: "Concise summary of the document"
Example 2: Multi-agent system with tools
agent = await spawn(
premise="You are a data analyst.",
scope={"analyze": my_analyzer, "query_db": db_query}
)
result: dict[str, int] = await agent.call(
dict[str, int],
"Analyze Q3 sales trends"
)
# Returns: {"growth": 23, "peak_month": 7}
Example 3: Agent coordination
researcher = await spawn(premise="Research expert")
writer = await spawn(premise="Technical writer")
findings = await researcher.call(str, "Research AI safety")
article = await writer.call(str, f"Write about: {findings}")
What's Included
- SKILL.md: Complete Agentica SDK reference with patterns and API documentation
- Quick Start Examples: @agentic decorator, spawn(), and multi-agent patterns
- Tool Integration Guide: MCP tool binding and scope management
- Type Safety Patterns: Return type specification and validation examples
- Prompting Framework: Premise vs system prompt strategies and customization
Who It's For
- Python developers building AI-powered applications
- AI/ML engineers implementing multi-agent systems
- Data scientists automating analysis workflows with agents
- Backend engineers integrating agentic capabilities into services
- DevOps/automation specialists orchestrating agent pipelines
Best For
- Creating AI-enhanced Python functions with minimal boilerplate
- Building multi-agent orchestration systems for complex workflows
- Integrating external tools and APIs with intelligent agents
- Implementing chatbots, researchers, and autonomous decision-makers
- Debugging and controlling agent behavior in production systems
You might also like
Conduct comprehensive fall risk assessments for patients 65+ by identifying modifiable risk factors including balance deficits, medication effects, neurological changes, and environmental hazards. Generate customized intervention plans that adjust treatment protocols based on individual risk profiles, with integrated documentation for liability protection and clinical decision-making that prioritizes patient safety throughout the care episode.
by aymericzip
You systematically evaluate sports injuries using clinical orthopedic testing procedures, document findings within the context of sport-specific biomechanical demands, and generate individualized rehabilitation protocols with clear functional milestones. This skill helps you create athlete-centered treatment plans that satisfy insurance documentation requirements while establishing realistic return-to-play timelines that athletes, coaches, and parents can understand and commit to.
by aymericzip
You can systematically coordinate complex schedules across multiple clinical disciplines, eliminate bottlenecks in patient flow, allocate shared rooms and equipment efficiently, and establish clear handoff procedures between providers. This skill helps you resolve scheduling conflicts, reduce provider idle time and patient wait times, and design communication protocols that keep all disciplines aligned on patient status and treatment plans.
by aymericzip
This skill transforms high-level feature requests into actionable implementation plans by conducting deep requirement interviews, analyzing existing codebases (or planning greenfield projects), and producing comprehensive handoff documents. It distinguishes between brownfield development (with existing code to integrate) and greenfield projects (starting from scratch), ensuring your technical strategy accounts for your actual constraints and patterns.
by moonwell-fi
You can architect multi-step autonomous AI workflows that move beyond simple prompting into persistent, stateful agent systems. This skill helps you define tool signatures, state schemas, decision logic, error recovery paths, and human checkpoint definitions—producing detailed Agent Specification Documents (ASDs) that development teams can implement without clarification meetings.
by moonwell-fi
You'll learn how to architect reliable multi-agent systems that scale with Claude, including patterns for agent coordination, failure recovery, and resource optimization. This skill guides you through designing agent hierarchies, implementing inter-agent communication protocols, and building observability into your system from the ground up—turning ad-hoc agent experiments into production-grade systems.
by moonwell-fi
You can conduct thorough fall risk assessments for geriatric patients by integrating validated screening instruments, functional mobility tests, spinal and neurological evaluation, and environmental risk factor analysis. The skill guides you through systematic documentation of findings, identifies modifiable risk factors specific to chiropractic intervention, and generates personalized prevention protocols that reduce fall probability while preserving patient autonomy and quality of life.
by aymericzip
You can conduct comprehensive sports injury evaluations that integrate mechanism of injury analysis, special orthopedic tests, and clinical reasoning to determine injury severity and return-to-sport readiness. This skill helps you create sport-specific treatment plans, document findings for third-party clearance, and differentiate between structural damage, functional limitations, and performance deficits—enabling you to make evidence-based decisions about athlete management and injury prevention strategies.
by aymericzip