agentify-core 0.4.0

Framework-agnostic AI agent library for building single and multi-agent systems

Agentify

Production-ready AI agent library built on the OpenAI SDK

Build and orchestrate AI agents—from simple assistants to complex multi-agent systems. Agentify targets the OpenAI-compatible Chat Completions interface, enabling seamless switching between providers (OpenAI, Azure, DeepSeek, Gemini, Anthropic, Llama, Local LLMs) without code changes.

---

Why Agentify?

Feature	Benefit
Production-first	Clear abstractions, explicit config, robust error handling
Multi-provider	Switch providers with one line—no agent code changes
Orchestration primitives	Uniform run()/arun() across agents, teams, pipelines, hierarchies
Async-native	Non-blocking I/O, parallel tool execution, event-loop friendly
Pluggable memory	In-memory, SQLite, Redis, Elasticsearch—same API
Local LLMs	Support for LM Studio, Ollama and custom local servers

---

Key Features

• Single agents & multi-agent patterns
  Agents with tools and memory • Supervisor–worker Teams • Sequential Pipelines • Hierarchical delegation • Dynamic routing

• Memory system
  Pluggable backends with policies (TTL, message limits, pruning) • Memory isolation per conversation • Async-safe operations

• Reasoning models
  Configurable thinking depth (reasoning_effort) • Chain-of-thought storage • Real-time reasoning logs

• Tools
  @tool decorator with automatic JSON Schema • Type-annotated interface • Argument validation

• Async & parallel execution
  Native arun() for async apps • run() bridge for sync apps • Parallel tool calls

• Observability
  Callback hooks for logging, monitoring, debugging

• Multimodal
  Vision/image support • Streaming responses

---

Installation

pip install agentify-core

Optional backends:

pip install agentify-core[redis]      # Redis memory store
pip install agentify-core[elastic]    # Elasticsearch store
pip install agentify-core[all]        # All optional dependencies

---

Quick Start

from agentify import BaseAgent, AgentConfig, MemoryService, MemoryAddress, tool
from agentify.memory.stores import InMemoryStore

@tool
def get_time() -> dict:
    """Returns the current time."""
    from datetime import datetime
    return {"time": datetime.now().strftime("%H:%M:%S")}

# Setup
memory = MemoryService(store=InMemoryStore())
addr = MemoryAddress(conversation_id="session_1")

agent = BaseAgent(
    config=AgentConfig(
        name="Assistant",
        system_prompt="You are a helpful assistant.",
        provider="provider",
        model_name="model",
        reasoning_effort="high",  # optional param:"low", "medium", "high"
        model_kwargs={"max_completion_tokens": 5000}, # Pass model-specific params       
        verbose=True, # Controls logging
    ),
    memory=memory,
    memory_address=addr,
    tools=[get_time],
)

response = agent.run("What time is it?")
print(response)

# Async usage is also available:
# response = await agent.arun("What time is it?")

---

Memory Backends

from agentify.memory.stores import InMemoryStore
from agentify.memory.stores.sqlite_store import SQLiteStore
from agentify.memory.stores.redis_store import RedisStore

# In-memory (default, for development)
store = InMemoryStore()

# SQLite (persistent, zero-config)
store = SQLiteStore(db_path="./agent.db")

# Redis (production, distributed)
store = RedisStore(url="redis://localhost:6379/0")

---

Composable Flows

All primitives share the same run()/arun() interface:

• BaseAgent — Single agent with tools
• Team — Supervisor routes to worker agents
• SequentialPipeline — Output flows step-to-step
• HierarchicalTeam — Tree structures for delegation

Nest freely: Teams of Pipelines, Pipelines of Teams, dynamic routing at runtime.

---

Links

• Documentation & Examples: GitHub Repository
• Issues & PRs: Contribute

---

License

MIT License

Author

Fabian Melchor — [e-mail]