Install the latest stable release from PyPI:
pip install agentic-ai-kitSet your Gemini API key before using the framework.
export GEMINI_API_KEY="your-key-here"
Google Colab
Store GEMINI_API_KEY in Colab Secrets and load it into os.environ before creating an agent.
Quick Start
from agentic_ai.agents import BaseAgentCapability Component
Simple conversational agents
BaseAgent
Persona and short-term memory
BaseAgent, ShortTermMemory
LLM-extracted durable facts
BaseAgent.facts_store
SQLite-backed long-term memory
LongTermMemory
Shared state across agents
SharedMemory
Gemini function-calling tools
ToolAgent, ToolRegistry
Structured JSON output
JsonAgent
Reasoning and planning workflows
ReasoningAgent
Round-robin conversations
run_conversation
Supervisor delegation
run_supervisor
Parallel fan-out execution
run_parallel
Debate and judge pattern
run_debate
Chunking, embeddings, and vector search
chunk_text, embed_texts, VectorStore
Retrieval-Augmented Generation (RAG)
RAGAgent
MCP-style tool server and client
MCPServer, MCPClient
DataFrame analysis
AnalystAgent
Machine learning model training
MLEAgent
End-to-end automated modelling workflow
AutoModelAgent
Package Layout
agentic_ai/├── agents/│ ├── base.py # BaseAgent — memory, streaming, durable facts│ ├── tool_agent.py # ToolAgent — Gemini function calling│ ├── json_agent.py # JsonAgent — structured JSON responses│ ├── reasoning_agent.py # ReasoningAgent — planning workflows│ ├── analyst_agent.py # AnalystAgent — dataframe profiling & analysis│ ├── mle_agent.py # MLEAgent — train & compare sklearn models│ └── auto_model_agent.py # AutoModelAgent — automated modelling workflow│├── memory/│ ├── short_term.py # Sliding-window conversational memory│ ├── long_term.py # SQLite-backed persistent memory│ └── shared.py # Thread-safe shared state│├── tools/│ ├── registry.py # @tool decorator & ToolRegistry│ └── builtins.py # Built-in utility tools│├── patterns/│ ├── orchestrator.py # Conversations & supervisor workflows│ ├── parallel.py # Parallel fan-out execution│ └── debate.py # Debate with judging│├── rag/│ ├── chunker.py # chunk_text│ ├── embedder.py # Gemini embeddings│ ├── vector_store.py # In-memory vector search│ └── rag_agent.py # Retrieval → Generation pipeline│└── mcp/ ├── server.py # MCPServer — HTTP tool server └── client.py # MCPClient — connects to MCPServer