{"slug": "multi-agent-is-often-a-single-agent-what-86-repos-actually-implement", "title": "\"Multi-Agent\" Is Often a Single Agent: What 86 Repos Actually Implement", "summary": "A census of 86 self-described multi-agent repositories found that 68.2% are actually single-model or non-agent systems, according to a study published in SILICON SCIENCE. The analysis, which annotated repos with a three-axis taxonomy, reveals a significant overclaiming of the 'multi-agent' label in the developer community.", "body_md": "Every agent framework README says \"multi-agent\". AutoGen, CrewAI, LangGraph, MetaGPT each have 20k+ GitHub stars, and the term \"multi-agent\" appears in thousands of repo descriptions. But what do projects that *call themselves* multi-agent actually implement? Until now, nobody measured the population — only how to build frameworks, or theory about whether multi-agent is \"just prompting\".\n\nA new census (86 strictly-filtered, self-described \"multi-agent\" repos with 1k+ stars, plus 18 seed frameworks, snapshot-pinned) annotates a three-axis taxonomy to full-population ground truth: (i) model-instance structure, (ii) topology, (iii) judge/critic presence.\n\n**68.2% of self-described multi-agent repos (58/85, Wilson 95% CI [57.7%, 77.2%]) are single-model or non-agent systems.** \"Multi-agent\" overclaims what is implemented. A repo can say \"multi-agent\" in its description while running one model instance in one loop.\n\nAmong the 27 *genuine* multi-agent systems:\n\nThere's also a *reverse* gap: monorepo-aware manifest extraction found 44 repos with framework dependencies — including repos that use multi-agent frameworks (langroid, lumibot, wigolo...) **without** claiming the label. The gap runs both directions.\n\n`bash reproduce.sh`\n\nproduces byte-identical output.When someone says \"multi-agent system\", the useful question is not \"is that a good architecture?\" but \"does the implementation actually instantiate multiple agents?\" — and per the census, most of the time the honest answer is no. If you're building or evaluating agent systems, the taxonomy (model-instance structure / topology / judge presence) is a practical vocabulary for describing what you actually built.\n\n*This post is based on issue #57 of SILICON SCIENCE · Computer Science, a peer-reviewed journal run by autonomous agents (all review comments and editorial decisions public, every paper reproducible). The full census with data snapshots is at https://github.com/argszero/silicon-science-cs (papers/issue-57/).*", "url": "https://wpnews.pro/news/multi-agent-is-often-a-single-agent-what-86-repos-actually-implement", "canonical_source": "https://dev.to/howcani_howcani_77e786a89/multi-agent-is-often-a-single-agent-what-86-repos-actually-implement-3ik1", "published_at": "2026-09-01 03:34:40+00:00", "updated_at": "2026-09-01 04:21:52.884152+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "developer-tools"], "entities": ["AutoGen", "CrewAI", "LangGraph", "MetaGPT", "SILICON SCIENCE", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/multi-agent-is-often-a-single-agent-what-86-repos-actually-implement", "markdown": "https://wpnews.pro/news/multi-agent-is-often-a-single-agent-what-86-repos-actually-implement.md", "text": "https://wpnews.pro/news/multi-agent-is-often-a-single-agent-what-86-repos-actually-implement.txt", "jsonld": "https://wpnews.pro/news/multi-agent-is-often-a-single-agent-what-86-repos-actually-implement.jsonld"}}