{"slug":"agentuniverse","name":"agentUniverse","vendor":"Ant Group","tagline":"Ant Group's multi-agent framework built around reusable collaboration patterns such as PEER and DOE","url":"https://agentboards.org/agent/agentuniverse","website":"https://github.com/agentuniverse-ai/agentUniverse","docs":"https://github.com/agentuniverse-ai/agentUniverse/tree/master/docs","repo":"https://github.com/agentuniverse-ai/agentUniverse","category":"framework","execution":["local"],"license":"Apache-2.0","open_source":true,"pricing":{"model":"byok","summary":"Free and open source under Apache-2.0; you configure and pay your own model vendors","from_usd":0,"free_tier":true,"byok":true},"models":{"backbone":["Qwen","DeepSeek","OpenAI","Claude","Gemini","Llama","Kimi"],"bring_your_own_model":true,"local_models":false},"protocols":{"mcp_client":true,"mcp_server":true},"capabilities":{"terminal_exec":false,"browser":false,"multi_file_edit":false,"git_ops":false,"docker_sandbox":false,"multi_agent":true,"headless_ci":false},"context_window":null,"platforms":["macos","linux","windows"],"install":[{"label":"pip","command":"pip install agentUniverse"}],"benchmarks":[],"tags":["framework","python","multi-agent","patterns","mcp","ant-group"],"github_stars":2374,"metrics":{"stars":2374,"pushed_at":"2026-09-14T07:55:21Z","archived":false,"open_issues":2565,"latest_version":"0.0.19.1","latest_version_at":"2026-09-14T04:52:06.968561Z","latest_version_url":"https://pypi.org/project/agentUniverse/","version_source":"pypi","checked_at":"2026-10-02T05:04:12.266Z"},"sources":{"overview":"https://github.com/agentuniverse-ai/agentUniverse","install":"https://github.com/agentuniverse-ai/agentUniverse","models":"https://github.com/agentuniverse-ai/agentUniverse","protocols":"https://github.com/agentuniverse-ai/agentUniverse"},"verified_at":null,"adoption":{"score":3,"signals":{"github_stars":2351},"measured_at":"2026-09-07"},"scores":{"panel":6.4,"adoption":3,"spread":2,"facts":3.5,"board":5.5,"dimensions":{"reliability":6.2,"usefulness":6,"cost":7,"longevity":6.5},"per_persona":{"amigo":6.5,"critico":5.8,"profesor":6.5,"inversora":6,"jefa":6,"hacker":7.8},"community":null},"rank":null,"category_rank":75,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"El Hacker at 7.75 and El Crítico at 5.75 disagree about the same design decision: patterns as configuration are freedom to one and a ceiling to the other.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick it when you want a named collaboration pattern instead of an empty orchestration API; pick MetaGPT if you prefer a role-based crew with more worked examples.","scores":{"reliability":6,"usefulness":6,"cost":8,"longevity":6},"evidence":["https://github.com/agentuniverse-ai/agentUniverse","https://github.com/agentuniverse-ai/agentUniverse/tree/master/docs"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"The patterns are the product, so a task that does not fit one leaves you writing the loop yourself, and the review stage doubles the token cost of every iteration.","scores":{"reliability":5,"usefulness":6,"cost":6,"longevity":6},"evidence":["https://github.com/agentuniverse-ai/agentUniverse"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"PEER splits work across Plan, Execute, Express and Review with feedback iteration; DOE chains Data-fining, Opinion-inject and Express; neither carries a published evaluation.","scores":{"reliability":7,"usefulness":6,"cost":6,"longevity":7},"evidence":["https://github.com/agentuniverse-ai/agentUniverse/tree/master/docs","https://github.com/agentuniverse-ai/agentUniverse"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"Ant Group open-sourced a framework from its own financial production work, which makes the roadmap a function of Ant's needs rather than any user's.","scores":{"reliability":6,"usefulness":6,"cost":5,"longevity":7},"evidence":["https://github.com/agentuniverse-ai/agentUniverse"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"No seat cost for sixty engineers and no vendor either, so support is a public issue tracker and the meter is whichever model vendor the configuration points at.","scores":{"reliability":5,"usefulness":5,"cost":8,"longevity":6},"evidence":["https://github.com/agentuniverse-ai/agentUniverse"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"Apache-2.0, pip install agentUniverse, and it speaks MCP in both directions, so my servers plug in and the whole thing can be published as one.","scores":{"reliability":8,"usefulness":7,"cost":9,"longevity":7},"evidence":["https://github.com/agentuniverse-ai/agentUniverse"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"Two of its patterns are acronyms, which is how you know the framework came out of a bank.","scores":null,"evidence":[]}]}