OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Mangaba AI

Mangaba AI is an open-source Python framework for building multi-agent applications from agent crews, tasks and event-driven flows, with documented support for ReAct, RAG, memory, multiple LLM providers, and MCP/A2A connections.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mangaba AI — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Mangaba AI when building a Python application that needs coordinated agents or event-driven orchestration, especially when the design also calls for RAG, memory or more than one LLM provider.

Who it is for

  • Python developers building applications that coordinate multiple AI agents.
  • Teams structuring agent work as crews or event-routed workflows.
  • Developers adding retrieval, memory, or multiple model providers to agent applications.

Documented uses

  • Define agents with roles, goals, tools and assigned tasks.
  • Coordinate tasks sequentially, hierarchically, in parallel or through a consensual crew process.
  • Build event-driven workflows with routing and typed state.
  • Connect agent applications to retrieval sources, memory, MCP tools or A2A interoperability.
Before you choose

Requirements & limits

The project is identified as MIT-licensed open-source software. The documented quick-start uses pip and a Google API key; other listed model-provider options include local Ollama and OpenAI-compatible servers.

  • The README lists four crew processes: sequential, hierarchical, parallel and consensual.
  • Flows support event-oriented start, listen and route patterns, with typed state and documented SQLite persistence.
  • The README describes RAG, embeddings, memory, vector stores, MCP tools and multiple LLM providers; optional RAG and embeddings are installed with pip install mangaba[all].
  • The repository documents a CLI and compatibility with several CrewAI OSS primitives, but does not claim that every existing project transfers unchanged.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Mangaba and run the quick-start example

Install the Python package, set a Google API key, and run the repository's quick-start script.

Before you start

  • Python environment with pip
  • Google API key
  • Repository checkout containing examples/quickstart.py

Steps

  1. Install the package with the command below.

    Documented command
    pip install mangaba

  2. Set the GOOGLE_API_KEY environment variable to your key.

  3. Run the command below from the repository.

    Documented command
    python examples/quickstart.py

Expected outcome

The documented quick-start example is invoked using the Google provider.

Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
Mangaba-ai/mangaba_ai · Official homepage title · retained in its source language
How we review sourcesSuggest a correction