AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917296330506240 |
|---|---|
| author | Pautsch, Erik Singla, Tanmay Kumar, Parv Jiang, Wenxin Peng, Huiyun Hassanshahi, Behnaz Läufer, Konstantin Thiruvathukal, George K. Davis, James C. |
| author_facet | Pautsch, Erik Singla, Tanmay Kumar, Parv Jiang, Wenxin Peng, Huiyun Hassanshahi, Behnaz Läufer, Konstantin Thiruvathukal, George K. Davis, James C. |
| contents | LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging Face). Existing efforts typically address naming, distribution, or protocol descriptors, but stop short of providing a registry layer that makes agents discoverable, comparable, and governable under automated reuse. We present AgentHub, a registry layer and accompanying research agenda for agent sharing that targets discovery and workflow integration, trust and security, openness and governance, ecosystem interoperability, lifecycle transparency, and capability clarity with evidence. We describe a reference prototype that implements a canonical manifest with publish-time validation, version-bound evidence records linked to auditable artifacts, and an append-only lifecycle event log whose states are respected by default in search and resolution. We also provide initial discovery results using an LLM-as-judge recommendation pipeline, showing how structured contracts and evidence improve intent-accurate retrieval beyond keyword-driven discovery. AgentHub aims to provide a common substrate for building reliable, reusable agent ecosystems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03495 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents Pautsch, Erik Singla, Tanmay Kumar, Parv Jiang, Wenxin Peng, Huiyun Hassanshahi, Behnaz Läufer, Konstantin Thiruvathukal, George K. Davis, James C. Software Engineering Artificial Intelligence LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging Face). Existing efforts typically address naming, distribution, or protocol descriptors, but stop short of providing a registry layer that makes agents discoverable, comparable, and governable under automated reuse. We present AgentHub, a registry layer and accompanying research agenda for agent sharing that targets discovery and workflow integration, trust and security, openness and governance, ecosystem interoperability, lifecycle transparency, and capability clarity with evidence. We describe a reference prototype that implements a canonical manifest with publish-time validation, version-bound evidence records linked to auditable artifacts, and an append-only lifecycle event log whose states are respected by default in search and resolution. We also provide initial discovery results using an LLM-as-judge recommendation pipeline, showing how structured contracts and evidence improve intent-accurate retrieval beyond keyword-driven discovery. AgentHub aims to provide a common substrate for building reliable, reusable agent ecosystems. |
| title | AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2510.03495 |