MCP.so
Sign In

Evo AI - AI Agents Platform

@evolutionapi

About Evo AI - AI Agents Platform

Evo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI models and services.

Overview

What is Evo AI - AI Agents Platform?

Evo AI is an open‑source platform for creating and managing AI agents, enabling integration with different AI models and services. It runs as a web application with a FastAPI backend and a Next.js frontend, and is designed for developers and teams building multi‑agent systems.

How to use Evo AI - AI Agents Platform?

Clone the repository, then set up the backend by creating a virtual environment, configuring the .env file, running database migrations (make alembic-upgrade), and seeding initial data. Set up the frontend by installing dependencies (pnpm install) and configuring NEXT_PUBLIC_API_URL. Start the backend with make run and the frontend with pnpm dev. Access the UI at http://localhost:3000, create an admin account, configure an MCP server, create a client, and build your first agent.

Key features of Evo AI - AI Agents Platform

  • Creation and management of AI agents
  • Integration with multiple language models (GPT‑4, Claude, etc.)
  • Client management and MCP server configuration
  • Google Agent Development Kit (ADK) as base framework
  • Agent‑to‑Agent (A2A) protocol support
  • Workflow agent with LangGraph
  • JWT authentication with email verification
  • Langfuse integration for tracing and observability

Use cases of Evo AI - AI Agents Platform

FAQ from Evo AI - AI Agents Platform

What AI engines does Evo AI support?

Google Agent Development Kit (ADK) is fully supported. CrewAI support is under development and not yet ready for production.

How do I install Evo AI?

Installation requires Python 3.10+, PostgreSQL 13+, Redis 6+, Node.js 18+, and pnpm. Follow the backend and frontend setup steps in the README, then run the services via make run and pnpm dev.

Is Evo AI free and open‑source?

Yes, it is licensed under Apache License 2.0.

Can I trace agent executions?

Yes, Langfuse is natively integrated via OpenTelemetry. Set the LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, and OTEL_EXPORTER_OTLP_ENDPOINT environment variables to enable tracing.

What authentication methods are available?

JWT authentication is used, with user registration, email verification, login, password recovery, and account lockout after multiple failed attempts.

Comments

More Agent Frameworks MCP clients