{"paper":{"title":"OpenJarvis: Personal AI, On Personal Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Andrew Park, Avanika Narayan, Azalia Mirhoseini, Caia Costello, Christopher R\\'e, Chuan Li, Gabriel Bo, Hakki Orhun Akengin, Herumb Shandilya, Jon Saad-Falcon, Matthew Hart, Robby Manihani, Tanvir Bhathal","submitted_at":"2026-05-16T22:00:10Z","abstract_excerpt":"Personal AI stacks, like OpenClaw and Hermes Agent, are becoming central to daily work, yet they route nearly every query (often over sensitive local data) to cloud-hosted frontier models. Replacing frontier models with local models inside existing stacks does not work: swapping Claude Opus 4.6 for Qwen3.5-9B drops accuracy by 25-39 pp across personal AI tasks like PinchBench and GAIA. Existing stacks bundle agentic prompts, tool descriptions, memory configuration, and runtime settings around a specific cloud model. Only the prompts can be tuned, and state-of-the-art prompt optimizers close ju"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17172","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17172/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.752354Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.977095Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"56cc4ca7328c1161cfbac32b05225bbfb9ae625b2387263994e99b132f46ddd4"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}