AI Agent Framework

Framework for building autonomous AI agents with tools

Category: agent
Version: 1.5.0
Deployment formats: Docker Compose, Helm (Kubernetes), Terraform (local Docker), Terraform (AWS)
Maintainer: AI Solutions Camp
Tags: AI Agents, LangGraph, Tools, Autonomous, Multi-Agent

Overview

A flexible framework for building autonomous AI agents with tool use, memory, and planning capabilities. Based on LangGraph with support for custom tools and multi-agent orchestration.

Requirements

Docker and Docker Compose installed
4GB RAM minimum
API keys for external LLMs (OpenAI, etc.) or local Ollama

Quick start

Quick Start (Docker)

Start Flowise:

   docker-compose up -d

Open the UI:

Go to http://localhost:3000
Login: admin / changeme123

Create your first agent:

Click "Add New" → "Chatflow"
Drag components from the sidebar
Connect: LLM → Agent → Tools

Optional - Add local LLM:

   docker exec -it ollama ollama pull llama3.2

In Flowise, use "ChatOllama" with URL: http://ollama:11434

Pre-built Templates:

Conversational Agent
ReAct Agent
RAG Pipeline
SQL Agent

Environment variables

FLOWISE_USERNAME (required) – Admin username for Flowise UI
FLOWISE_PASSWORD (required) – Admin password for Flowise UI
APIKEY_PATH – Path to store API keys
LOG_LEVEL – Logging level

docker-compose.yml

version: "3.8"

services:
  flowise:
    image: flowiseai/flowise:latest
    container_name: flowise
    ports:
      - "3000:3000"
    volumes:
      - flowise_data:/root/.flowise
    environment:
      - FLOWISE_USERNAME=admin
      - FLOWISE_PASSWORD=changeme123
      - APIKEY_PATH=/root/.flowise
      - SECRETKEY_PATH=/root/.flowise
      - LOG_LEVEL=info
    restart: unless-stopped

  # Optional: Add Ollama for local LLM
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    restart: unless-stopped

volumes:
  flowise_data:
  ollama_data: