{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RF4YR3SKYJNCISOHBA3AZ3JYC4","short_pith_number":"pith:RF4YR3SK","schema_version":"1.0","canonical_sha256":"897988ee4ac25a2449c708360ced381708379ee0350a6861da4fb1ebf7d1f846","source":{"kind":"arxiv","id":"2506.06326","version":1},"attestation_state":"computed","paper":{"title":"Memory OS of AI Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiazheng Kang, Mingming Ji, Ting Bai, Zhe Zhao","submitted_at":"2025-05-30T15:36:51Z","abstract_excerpt":"Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with AI agents. To overcome this challenge, we innovatively propose a Memory Operating System, i.e., MemoryOS, to achieve comprehensive and efficient memory management for AI agents. Inspired by the memory management principles in operating systems, MemoryOS designs a hierarchical storage architecture and consists of four key modules: Memory Storage, Updating, Re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.06326","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T15:36:51Z","cross_cats_sorted":[],"title_canon_sha256":"cea2a4a983b613311aeaf3862c90ac9731f2132c43d6b9f32a685921818dff62","abstract_canon_sha256":"f6fb6a49c2a514a9f81d48edc27166a8ceef86780588a673478d8757a93e3e93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:48.066670Z","signature_b64":"Z5mnq7+qGDyO4asGtI0xkp9uRY38+nevpqBO1GoKq8IMr94TXq4cAsz9+q+zpmBfs+zvs48f4l7RYH4qBbCpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"897988ee4ac25a2449c708360ced381708379ee0350a6861da4fb1ebf7d1f846","last_reissued_at":"2026-07-05T11:17:48.066189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:48.066189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory OS of AI Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiazheng Kang, Mingming Ji, Ting Bai, Zhe Zhao","submitted_at":"2025-05-30T15:36:51Z","abstract_excerpt":"Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with AI agents. To overcome this challenge, we innovatively propose a Memory Operating System, i.e., MemoryOS, to achieve comprehensive and efficient memory management for AI agents. Inspired by the memory management principles in operating systems, MemoryOS designs a hierarchical storage architecture and consists of four key modules: Memory Storage, Updating, Re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06326","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/2506.06326/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.06326","created_at":"2026-07-05T11:17:48.066246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06326v1","created_at":"2026-07-05T11:17:48.066246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06326","created_at":"2026-07-05T11:17:48.066246+00:00"},{"alias_kind":"pith_short_12","alias_value":"RF4YR3SKYJNC","created_at":"2026-07-05T11:17:48.066246+00:00"},{"alias_kind":"pith_short_16","alias_value":"RF4YR3SKYJNCISOH","created_at":"2026-07-05T11:17:48.066246+00:00"},{"alias_kind":"pith_short_8","alias_value":"RF4YR3SK","created_at":"2026-07-05T11:17:48.066246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05794","citing_title":"From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00017","citing_title":"Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00017","citing_title":"Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26870","citing_title":"Persistent AI Agents in Academic Research: A Single-Investigator Implementation Case Study","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30306","citing_title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28773","citing_title":"Rethinking Memory as Continuously Evolving Connectivity","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30771","citing_title":"Eywa: Provenance-Grounded Long-Term Memory for AI Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06036","citing_title":"Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21768","citing_title":"Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15701","citing_title":"H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05257","citing_title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09568","citing_title":"EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07957","citing_title":"MIRIX: Multi-Agent Memory System for LLM-Based Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01707","citing_title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08460","citing_title":"When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09942","citing_title":"HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12285","citing_title":"GAM: Hierarchical Graph-based Agentic Memory for LLM Agents","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15877","citing_title":"Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RF4YR3SKYJNCISOHBA3AZ3JYC4","json":"https://pith.science/pith/RF4YR3SKYJNCISOHBA3AZ3JYC4.json","graph_json":"https://pith.science/api/pith-number/RF4YR3SKYJNCISOHBA3AZ3JYC4/graph.json","events_json":"https://pith.science/api/pith-number/RF4YR3SKYJNCISOHBA3AZ3JYC4/events.json","paper":"https://pith.science/paper/RF4YR3SK"},"agent_actions":{"view_html":"https://pith.science/pith/RF4YR3SKYJNCISOHBA3AZ3JYC4","download_json":"https://pith.science/pith/RF4YR3SKYJNCISOHBA3AZ3JYC4.json","view_paper":"https://pith.science/paper/RF4YR3SK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06326&json=true","fetch_graph":"https://pith.science/api/pith-number/RF4YR3SKYJNCISOHBA3AZ3JYC4/graph.json","fetch_events":"https://pith.science/api/pith-number/RF4YR3SKYJNCISOHBA3AZ3JYC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RF4YR3SKYJNCISOHBA3AZ3JYC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RF4YR3SKYJNCISOHBA3AZ3JYC4/action/storage_attestation","attest_author":"https://pith.science/pith/RF4YR3SKYJNCISOHBA3AZ3JYC4/action/author_attestation","sign_citation":"https://pith.science/pith/RF4YR3SKYJNCISOHBA3AZ3JYC4/action/citation_signature","submit_replication":"https://pith.science/pith/RF4YR3SKYJNCISOHBA3AZ3JYC4/action/replication_record"}},"created_at":"2026-07-05T11:17:48.066246+00:00","updated_at":"2026-07-05T11:17:48.066246+00:00"}