AI AGENTS
MiroFlow
by MiroMindAI
Overview
MiroFlow is an agentic AI platform for building intelligent agents with tool integration, benchmark evaluations, and a web UI.
Details
MiroFlow is described by its documentation as an agentic AI platform for building intelligent agents with tool integration, benchmark evaluations, and quick-start documentation. Its core concepts cover workflows for intent recognition, planning, sub-agent delegation, MCP tool access, and result synthesis. The GitHub repository excerpt also highlights a web UI, benchmark performance, and support for MiroThinker, Claude, Kimi, and OpenAI.
When to Use
Build or evaluate agentic AI workflows that need planning tool access sub-agent delegation and result synthesis. Experiment with an agent platform that documents benchmark evaluations and provides quick-start material. Explore a web-UI-based agent framework with support for MiroThinker Claude Kimi and OpenAI.
Getting Started
- Open the official documentation at https://miromindai.github.io/MiroFlow/ and review the quick-start material.
- Read the core concepts page to understand intent recognition
- planning
- sub-agent delegation
- MCP tool access
- and result synthesis.
- Inspect the GitHub repository at https://github.com/MiroMindAI/MiroFlow for project files
- setup instructions
- and examples before production use.
Key Features
- •Agentic AI platform for building intelligent agents
- •Tool integration
- •including MCP tool access described in the core concepts documentation
- •Workflow concepts for intent recognition
- •planning
- •sub-agent delegation
- •and result synthesis
- •Web UI highlighted in the GitHub repository excerpt
- •Benchmark evaluation focus highlighted in the documentation and repository excerpt
- •Support for MiroThinker
- •Claude
- •Kimi
- •and OpenAI noted in the repository excerpt
Capabilities
- •agentic-workflows
- •tool-integration
- •planning
- •sub-agent-delegation
- •mcp-tool-access
- •benchmark-evaluation
- •web-ui
Last updated Jun 4, 2026