{"slug": "eywa-local-first-memory-for-ai-agents-with-a-receipt-for-every-fact", "title": "Eywa: Local-first memory for AI agents, with a receipt for every fact", "summary": "Researchers introduced Eywa, a provenance-grounded long-term memory architecture for AI agents that stores immutable source evidence before deriving facts, achieving 90.19% judge accuracy on the LoCoMo benchmark and 88.2% retrieval-sufficiency accuracy on LongMemEval-S. The system validates extracted memories against typed signals and source support, retrieving bounded context through a deterministic multi-route read path with zero LLM calls inside retrieval, enabling diagnosis of failures across evidence, extraction, state, retrieval, or answer-model behavior.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 29 May 2026]\n\n# Title:Eywa: Provenance-Grounded Long-Term Memory for AI Agents\n\n[View PDF](/pdf/2605.30771)\n\n[HTML (experimental)](https://arxiv.org/html/2605.30771v1)\n\nAbstract:AI agents that persist across sessions need memory they can retrieve, audit, update, and erase. Existing memory systems often collapse source evidence, extracted facts, retrieved context, and answer policy into one opaque prompt path, making failures difficult to diagnose: a wrong answer may come from missing evidence, unsupported extraction, stale state, retrieval loss, or answer-model behavior. We present Eywa, a provenance-grounded memory architecture built around evidence before belief. Eywa stores immutable source evidence before deriving canonical facts, validates extracted memories against typed signals and source support, and retrieves bounded memory context through a deterministic multi-route read path with zero LLM calls inside retrieval. Retrieved context is returned separately from answer instructions, allowing the same memory substrate to be evaluated across frontier, budget, and local answer models. Under a frozen, artifact-recorded retrieval configuration, Eywa reaches 90.19% judge accuracy on the LoCoMo C1-C4 split with Claude Sonnet 4.6 write and QA roles. On LongMemEval-S, it reaches 88.2% retrieval-sufficiency accuracy. On BEAM, a 700-question technical-memory stress benchmark, it reaches 81.45% mean nugget score and 85.29% pass@score >= 0.5. Full per-question artifacts, including questions, gold answers, model answers, retrieved context, and labels, are published at[this https URL].\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/eywa-local-first-memory-for-ai-agents-with-a-receipt-for-every-fact", "canonical_source": "https://arxiv.org/abs/2605.30771", "published_at": "2026-06-13 17:57:21+00:00", "updated_at": "2026-06-13 18:17:23.497544+00:00", "lang": "en", "topics": ["ai-agents", "ai-research", "large-language-models", "artificial-intelligence"], "entities": ["Eywa", "LoCoMo", "LongMemEval-S", "BEAM", "Claude Sonnet 4.6"], "alternates": {"html": "https://wpnews.pro/news/eywa-local-first-memory-for-ai-agents-with-a-receipt-for-every-fact", "markdown": "https://wpnews.pro/news/eywa-local-first-memory-for-ai-agents-with-a-receipt-for-every-fact.md", "text": "https://wpnews.pro/news/eywa-local-first-memory-for-ai-agents-with-a-receipt-for-every-fact.txt", "jsonld": "https://wpnews.pro/news/eywa-local-first-memory-for-ai-agents-with-a-receipt-for-every-fact.jsonld"}}