{"slug":"miroflow","name":"MiroFlow","vendor":"MiroMindAI","tagline":"A high-performance, modular framework for building intelligent AI agents, featuring multi-turn conversation and sub-agent orchestration.","url":"https://agentboards.org/agent/miroflow","website":"https://miromind.ai/blog/miroflow","docs":"https://miromindai.github.io/MiroFlow/","repo":"https://github.com/MiroMindAI/MiroFlow","category":"framework","execution":["local"],"license":"Apache-2.0","open_source":true,"pricing":{"model":"byok","summary":"Relies on API keys for models, can run MiroThinker locally.","from_usd":null,"free_tier":false,"byok":true},"models":{"backbone":["GPT","Claude","Gemini","Qwen","MiroThinker"],"bring_your_own_model":true,"local_models":true},"protocols":{"mcp_client":false,"mcp_server":true},"capabilities":{"terminal_exec":true,"browser":true,"multi_file_edit":true,"git_ops":false,"docker_sandbox":false,"multi_agent":true,"headless_ci":false},"context_window":null,"platforms":["linux","macos"],"install":[{"label":"Clone and setup","command":"git clone https://github.com/MiroMindAI/MiroFlow && cd MiroFlow\nuv sync"},{"label":"Configure API key","command":"cp .env.template .env"},{"label":"Run your first agent","command":"uv run main.py trace --config_file_name=agent_quickstart_reading --task=\"What is the first country listed in the XLSX file that have names starting with Co?\" --task_file_name=\"data/FSI-2023-DOWNLOAD.xlsx\""}],"benchmarks":[],"tags":["research","orchestration","tool-use","benchmarks","auto-listed"],"github_stars":3117,"metrics":{"stars":3117,"pushed_at":"2026-07-06T14:50:43Z","archived":false,"open_issues":1,"latest_version":null,"latest_version_at":null,"latest_version_url":null,"version_source":null,"checked_at":"2026-10-02T05:03:37.372Z"},"sources":{"license":"https://github.com/MiroMindAI/MiroFlow","models":"https://github.com/MiroMindAI/MiroFlow","capabilities":"https://github.com/MiroMindAI/MiroFlow","install":"https://github.com/MiroMindAI/MiroFlow"},"verified_at":null,"adoption":{"score":3.4,"signals":{"github_stars":3113},"measured_at":"2026-09-21"},"scores":{"panel":5.6,"adoption":3.4,"spread":5,"facts":4.7,"board":5.1,"dimensions":{"reliability":4.8,"usefulness":5.7,"cost":6.5,"longevity":5.3},"per_persona":{"amigo":6.5,"critico":6,"profesor":4.8,"inversora":5.8,"jefa":2.8,"hacker":7.8},"community":null},"rank":null,"category_rank":98,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"The panel splits five points on whether MiroFlow's lack of a sandbox is a feature or a fatal flaw.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick MiroFlow if you are a researcher building agents for complex reasoning tasks and want a powerful, open-source orchestration framework you can run yourself.","scores":{"reliability":5,"usefulness":6,"cost":9,"longevity":6},"evidence":["https://miromind.ai/blog/miroflow","https://github.com/MiroMindAI/MiroFlow"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"MiroFlow executes local code without a sandbox, exposing the host machine to risks from agent-generated commands.","scores":{"reliability":3,"usefulness":6,"cost":8,"longevity":7},"evidence":["https://miromind.ai/blog/miroflow","https://github.com/MiroMindAI/MiroFlow"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"MiroFlow is a research framework for agent orchestration with self-reported benchmark scores and a dependency on a custom local model for cost-effective deployment.","scores":{"reliability":3,"usefulness":5,"cost":6,"longevity":5},"evidence":["https://miromind.ai/blog/miroflow","https://github.com/MiroMindAI/MiroFlow"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"A well-executed research framework with strong benchmark performance, but its business model is unclear, making it a classic feature play for a larger platform.","scores":{"reliability":8,"usefulness":7,"cost":3,"longevity":5},"evidence":["https://miromind.ai/blog/miroflow","https://github.com/MiroMindAI/MiroFlow"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"This is a research framework, not a product; there is nothing here to procure.","scores":{"reliability":2,"usefulness":3,"cost":4,"longevity":2},"evidence":["https://miromind.ai/blog/miroflow","https://github.com/MiroMindAI/MiroFlow"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"MiroFlow is a solid, open-source research framework you can run on your own hardware, but its power to execute arbitrary code means you better trust what you're running.","scores":{"reliability":8,"usefulness":7,"cost":9,"longevity":7},"evidence":["https://miromind.ai/blog/miroflow","https://github.com/MiroMindAI/MiroFlow"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"This research agent framework has multi-agent capabilities but lacks a sandboxed environment for execution.","scores":null,"evidence":[]}]}