Agentica SdkSAFE

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: agentica-sdk
description: Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
allowed-tools: [Bash, Read, Write, Edit]
---

# Agentica SDK Reference (v0.3.1)

Build AI agents in Python using the Agentica framework. Agents can implement functions, maintain state, use tools, and coordinate with each other.

## When to Use

Use this skill when:
- Building new Python agents
- Adding agentic capabilities to existing code
- Integrating MCP tools with agents
- Implementing multi-agent orchestration
- Debugging agent behavior

## Quick Start

### Agentic Function (simplest)

```python
from agentica import agentic

@agentic()
async def add(a: int, b: int) -> int:
    """Returns the sum of a and b"""
    ...

result = await add(1, 2)  # Agent computes: 3
```

### Spawned Agent (more control)

```python
from agentica import spawn

agent = await spawn(premise="You are a truth-teller.")
result: bool = await agent.call(bool, "The Earth is flat")
# Returns: False
```

## Core Patterns

### Return Types

```python
# String (default)
result = await agent.call("What is 2+2?")

# Typed output
result: int = await agent.call(int, "What is 2+2?")
result: dict[str, int] = await agent.call(dict[str, int], "Count items")

# Side-effects only
await agent.call(None, "Send message to John")
```

### Premise vs System Prompt

```python
# Premise: adds to default system prompt
agent = await spawn(premise="You are a math expert.")

# System: full control (replaces default)
agent = await spawn(system="You are a JSON-only responder.")
```

### Passing Tools (Scope)

```python
from agentica import agentic, spawn

# In decorator
@agentic(scope={'web_search': web_search_fn})
async def researcher(query: str) -> str:
    """Research a topic."""
    ...

# In spawn
agent = await spawn(
    premise="Data analyzer",
    scope={"analyze": custom_analyzer}
)

# Per-call scope
result = await agent.call(
    dict[str, int],
    "Analyze the dataset",
    dataset=data,           # Available as 'dataset'
    analyzer=custom_fn      # Available as 'analyzer'
)
```

### SDK Integration Pattern

```python
from slack_sdk import WebClient

slack = WebClient(token=SLACK_TOKEN)

# Extract specific methods
@agentic(scope={
    'list_users': slack.users_list,
    'send_message': slack.chat_postMessage
})
async def team_notifier(message: str) -> None:
    """Send team notifications."""
    ...
```

## Agent Instantiation

### spawn() - Async (most cases)

```python
agent = await spawn(premise="Helpful assistant")
```

### Agent() - Sync (for `__init__`)

```python
from agentica.agent import Agent

class CustomAgent:
    def __init__(self):
        # Synchronous - use Agent() not spawn()
        self._brain = Agent(
            premise="Specialized assistant",
            scope={"tool": some_tool}
        )

    async def run(self, task: str) -> str:
        return await self._brain(str, task)
```

## Model Selection

```python
# In spawn
agent = await spawn(
    premise="Fast responses",
    model="openai:gpt-5"  # Default: openai:gpt-4.1
)

# In decorator
@agentic(model="anthropic:claude-sonnet-4.5")
async def analyze(text: str) -> dict:
    """Analyze text."""
    ...
```

**Available models:**
- `openai:gpt-3.5-turbo`, `openai:gpt-4o`, `openai:gpt-4.1`, `openai:gpt-5`
- `anthropic:claude-sonnet-4`, `anthropic:claude-opus-4.1`
- `anthropic:claude-sonnet-4.5`, `anthropic:claude-opus-4.5`
- Any OpenRouter slug (e.g., `google/gemini-2.5-flash`)

## Persistence (Stateful Agents)

```python
@agentic(persist=True)
async def chatbot(message: str) -> str:
    """Remembers conversation history."""
    ...

await chatbot("My name is Alice")
await chatbot("What's my name?")  # Knows: Alice
```

For `spawn()` agents, state is automatic across calls to the same instance.

## Token Limits

```python
from agentica import spawn, MaxTokens

# Simple limit
agent = await spawn(
    premise="Brief responses",
    max_tokens=500
)

# Fine-grained control
agent = await spawn(
    premise="Controlled output",
    max_tokens=MaxTokens(
        per_invocation=5000,  # Total across all rounds
        per_round=1000,       # Per inference round
        rounds=5              # Max inference rounds
    )
)
```

## Token Usage Tracking

```python
from agentica import spawn, last_usage, total_usage

agent = await spawn(premise="You are helpful.")
await agent.call(str, "Hello!")

# Agent method
usage = agent.last_usage()
print(f"Last: {usage.input_tokens} in, {usage.output_tokens} out")

usage = agent.total_usage()
print(f"Total: {usage.total_tokens} processed")

# For @agentic functions
@agentic()
async def my_fn(x: str) -> str: ...

await my_fn("test")
print(last_usage(my_fn))
print(total_usage(my_fn))
```

## Streaming

```python
from agentica import spawn
from agentica.logging.loggers import StreamLogger
import asyncio

agent = await spawn(premise="You are helpful.")

stream = StreamLogger()
with stream:
    result = asyncio.create_task(
        agent.call(bool, "Is Paris the capital of France?")
    )

# Consume stream FIRST for live output
async for chunk in stream:
    print(chunk.content, end="", flush=True)
# chunk.role is 'user', 'agent', or 'system'

# Then await result
final = await result
```

## MCP Integration

```python
from agentica import spawn, agentic

# Via config file
agent = await spawn(
    premise="Tool-using agent",
    mcp="path/to/mcp_config.json"
)

@agentic(mcp="path/to/mcp_config.json")
async def tool_user(query: str) -> str:
    """Uses MCP tools."""
    ...
```

**mcp_config.json format:**
```json
{
  "mcpServers": {
    "tavily-remote-mcp": {
      "command": "npx -y mcp-remote https://mcp.tavily.com/mcp/?tavilyApiKey=<key>",
      "env": {}
    }
  }
}
```

## Logging

### Default Behavior
- Prints to stdout with colors
- Writes to `./logs/agent-<id>.log`

### Contextual Logging

```python
from agentica.logging.loggers import FileLogger, PrintLogger
from agentica.logging.agent_logger

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

.claude/scripts/mcp

Gates applied: no_behavioural_pass.

[![ModelsAtlas audit: Agentica Sdk](https://modelsatlas.com/skills/parcadei/agentica-sdk/badge.svg)](https://modelsatlas.com/skills/parcadei/agentica-sdk/)

Not your listing, or something out of date? Claim or update your listing.