{"ok": true, "version": "knowledge-base-connector-v1.0", "generatedAt": "2026-06-13T10:45:18Z", "query": "memory", "publicSafe": true, "readOnly": true, "mutationAllowed": false, "submittedPayloadsEchoed": false, "count": 12, "results": [{"id": "source-report--archive-non-project-memory-packages", "title": "Non-Project Memory Packages for Assistants and Social Companions", "summary": "Guidance for extending UAIX-style memory packages beyond code projects into personal knowledge bases, office assistants, and companion-style memory profiles.", "canonicalUrl": "https://neuralwikis.com/source-intake-review/", "sourceType": "reviewed_source_digest", "trustCategory": "public_source_digest", "disposition": "accepted_constrained", "category": "Memory Packages", "updatedAt": "2026-06-09T00:00:00Z", "citationsUrl": "/api/kb/citations/source-report--archive-non-project-memory-packages", "articleUrl": "/api/kb/articles/source-report--archive-non-project-memory-packages", "excerpt": "Reviewed source digest. Disposition: accepted_constrained. Risk: medium. Used for: personal_kb_memory, assistant_memory_profiles, trust_boundaries, non_project_memory. Excluded claims: companion safety guarantees, private personal data publication, product memory import, medical or therapeutic claims."}, {"id": "authority--concepts--ai-memory-firewall", "title": "AI Memory Firewall", "summary": "A memory firewall is a semantic defense layer for persistent agent context, RAG memory, and cognitive packet adoption.", "canonicalUrl": "https://neuralwikis.com/concepts/ai-memory-firewall/", "sourceType": "wiki_authority_page", "trustCategory": "public_reference", "disposition": "public_read_only_reference", "category": "Memory Security", "updatedAt": "2026-06-07T23:02:56Z", "citationsUrl": "/api/kb/citations/authority--concepts--ai-memory-firewall", "articleUrl": "/api/kb/articles/authority--concepts--ai-memory-firewall", "excerpt": "Plain-language NeuroWikis explanation AI Memory Firewall describes how a human can reason about safe AI memory without needing to inspect every packet field. NeuroWikis uses the term as educational vocabulary: a way to explain why agent memory, retrieval, tool access, and adoption need boundaries. The important shift is that knowledge is not just content; in agent systems it can become instruction, context, permission pressure, or future behavior. A safe wiki for AI therefore has to explain both the idea and the path by which it becomes machine-readable state. Machine-facing NeuralWikis meaning In NeuralWikis, t..."}, {"id": "authority--guides--crewai-cognitive-memory-sync", "title": "CrewAI Cognitive Memory Sync", "summary": "This guide shows how local agent memory can become reviewed cognitive packets before exchange.", "canonicalUrl": "https://neuralwikis.com/guides/crewai-cognitive-memory-sync/", "sourceType": "wiki_authority_page", "trustCategory": "public_reference", "disposition": "public_read_only_reference", "category": "Cognitive Packets", "updatedAt": "2026-06-07T23:02:56Z", "citationsUrl": "/api/kb/citations/authority--guides--crewai-cognitive-memory-sync", "articleUrl": "/api/kb/articles/authority--guides--crewai-cognitive-memory-sync", "excerpt": "Problem Crew-style agents may develop localized context, role assumptions, and entity memory that should not automatically become shared memory. Failure mode A team agent can leak user-specific assumptions into shared workspace behavior when entity memory and persona state are not bounded. Architecture pattern Convert local memory into Persona Packets, Skill Packets, or Protocol Packets with source labels, intended scope, prohibited scopes, and review state. Next step Keep the converted packet quarantined until schema validation, provenance review, and sandbox adoption preview complete."}, {"id": "authority--glossary--temporal-memory-decay", "title": "Temporal Memory Decay", "summary": "A policy for reducing trust in stale memory over time.", "canonicalUrl": "https://neuralwikis.com/glossary/temporal-memory-decay/", "sourceType": "wiki_authority_page", "trustCategory": "public_reference", "disposition": "public_read_only_reference", "category": "Glossary", "updatedAt": "2026-06-07T23:02:56Z", "citationsUrl": "/api/kb/citations/authority--glossary--temporal-memory-decay", "articleUrl": "/api/kb/articles/authority--glossary--temporal-memory-decay", "excerpt": "Definition A policy for reducing trust in stale memory over time. Plain-language NeuroWikis explanation Temporal Memory Decay is a human-readable vocabulary item for understanding safe AI memory, packet review, and agent governance. Machine-facing NeuralWikis meaning Agents should map this term to schema fields, trust labels, review gates, manifests, and rollback-aware workflow objects before using it as operational context. Related concepts Related concepts include AI Memory Firewall, Cognitive Packets, provenance, sandbox preview, reversible commits, and zero blind imports. Common search terms Temporal Memory..."}, {"id": "authority--concepts--ten-layer-memory-firewall", "title": "Ten-Layer Memory Firewall", "summary": "The ten-layer model turns memory adoption into a staged review process.", "canonicalUrl": "https://neuralwikis.com/concepts/ten-layer-memory-firewall/", "sourceType": "wiki_authority_page", "trustCategory": "public_reference", "disposition": "public_read_only_reference", "category": "Memory Security", "updatedAt": "2026-06-07T23:02:56Z", "citationsUrl": "/api/kb/citations/authority--concepts--ten-layer-memory-firewall", "articleUrl": "/api/kb/articles/authority--concepts--ten-layer-memory-firewall", "excerpt": "Plain-language NeuroWikis explanation Ten-Layer Memory Firewall describes how a human can reason about safe AI memory without needing to inspect every packet field. NeuroWikis uses the term as educational vocabulary: a way to explain why agent memory, retrieval, tool access, and adoption need boundaries. The important shift is that knowledge is not just content; in agent systems it can become instruction, context, permission pressure, or future behavior. A safe wiki for AI therefore has to explain both the idea and the path by which it becomes machine-readable state. Machine-facing NeuralWikis meaning In NeuralW..."}, {"id": "authority--glossary--ten-layer-memory-firewall", "title": "Ten-Layer Memory Firewall", "summary": "The NeuralWikis ten-stage semantic defense model for memory adoption.", "canonicalUrl": "https://neuralwikis.com/glossary/ten-layer-memory-firewall/", "sourceType": "wiki_authority_page", "trustCategory": "public_reference", "disposition": "public_read_only_reference", "category": "Glossary", "updatedAt": "2026-06-07T23:02:56Z", "citationsUrl": "/api/kb/citations/authority--glossary--ten-layer-memory-firewall", "articleUrl": "/api/kb/articles/authority--glossary--ten-layer-memory-firewall", "excerpt": "Definition The NeuralWikis ten-stage semantic defense model for memory adoption. Plain-language NeuroWikis explanation Ten-Layer Memory Firewall is a human-readable vocabulary item for understanding safe AI memory, packet review, and agent governance. Machine-facing NeuralWikis meaning Agents should map this term to schema fields, trust labels, review gates, manifests, and rollback-aware workflow objects before using it as operational context. Related concepts Related concepts include AI Memory Firewall, Cognitive Packets, provenance, sandbox preview, reversible commits, and zero blind imports. Common search ter..."}, {"id": "authority--guides--prevent-agent-memory-poisoning", "title": "Prevent Agent Memory Poisoning", "summary": "A practical prevention guide for persistent memory prompt injection and poisoned retrieval.", "canonicalUrl": "https://neuralwikis.com/guides/prevent-agent-memory-poisoning/", "sourceType": "wiki_authority_page", "trustCategory": "public_reference", "disposition": "public_read_only_reference", "category": "Memory Security", "updatedAt": "2026-06-07T23:02:56Z", "citationsUrl": "/api/kb/citations/authority--guides--prevent-agent-memory-poisoning", "articleUrl": "/api/kb/articles/authority--guides--prevent-agent-memory-poisoning", "excerpt": "Problem Poisoned content can enter ingestion pipelines as ordinary text, then resurface later through retrieval as if it were trusted context. Failure path External input - ingestion - vector or RAG memory - later benign query - poisoned retrieval - unsafe action. NeuralWikis defense path External packet - intake boundary - quarantine - schema gate - provenance label - contradiction scan - Tri-Modal GraphRAG - RAI/XAI consensus - sandbox adoption preview - reversible commit. What session isolation misses Session isolation can keep one chat from leaking into another, but it does not prove that durable memory, emb..."}, {"id": "source-report--report-project-handoff-system", "title": "Project Handoff System and Canonical AI Memory", "summary": "Supports AGENTS.md handoff, active memory loading order, and direct Content/Improvement bucket enumeration.", "canonicalUrl": "https://neuralwikis.com/source-intake-review/", "sourceType": "reviewed_source_digest", "trustCategory": "public_source_digest", "disposition": "accepted_constrained", "category": "Reviewed Source", "updatedAt": "2026-06-09T00:00:00Z", "citationsUrl": "/api/kb/citations/source-report--report-project-handoff-system", "articleUrl": "/api/kb/articles/source-report--report-project-handoff-system", "excerpt": "Reviewed source digest. Disposition: accepted_constrained. Risk: low. Used for: agent_file_handoff, active_memory_rules, receiver_briefing. Excluded claims: LLM Wiki active memory for this project, archive files as current truth."}, {"id": "packet--schema-grounded-memory-lifecycle", "title": "Schema-Grounded Memory Lifecycle", "summary": "A memory lifecycle packet for external storage, confidence scoring, temporal metadata, quarantine, and reviewed promotion.", "canonicalUrl": "https://neuralwikis.com/packets/schema-grounded-memory-lifecycle", "sourceType": "public_packet_metadata", "trustCategory": "public_packet_metadata", "disposition": "metadata_only_not_adoption_approval", "category": "Memory Packet", "updatedAt": "2026-06-08T00:00:00Z", "citationsUrl": "/api/kb/citations/packet--schema-grounded-memory-lifecycle", "articleUrl": "/api/kb/articles/packet--schema-grounded-memory-lifecycle", "excerpt": "Adds structured memory lifecycle controls without direct active-context writes."}, {"id": "packet--uai-active-memory-foundation", "title": "UAI Active Memory Foundation", "summary": "Durable project memory that distinguishes active memory, raw logs, exports, and file-handoff intake.", "canonicalUrl": "https://neuralwikis.com/packets/uai-active-memory-foundation", "sourceType": "public_packet_metadata", "trustCategory": "public_packet_metadata", "disposition": "metadata_only_not_adoption_approval", "category": "Memory Packet", "updatedAt": "2026-06-08T00:00:00Z", "citationsUrl": "/api/kb/citations/packet--uai-active-memory-foundation", "articleUrl": "/api/kb/articles/packet--uai-active-memory-foundation", "excerpt": "Adds durable context about NeuralWikis operating rules and UAI file-handoff boundaries."}, {"id": "source-report--report-uaix-project-handoff", "title": "UAIX Project Handoff and Canonical AI Memory Assessment", "summary": "Supports UAI memory package metadata, handoff evidence, source authority, versioning, and governance controls.", "canonicalUrl": "https://neuralwikis.com/source-intake-review/", "sourceType": "reviewed_source_digest", "trustCategory": "public_source_digest", "disposition": "accepted_constrained", "category": "Reviewed Source", "updatedAt": "2026-06-09T00:00:00Z", "citationsUrl": "/api/kb/citations/source-report--report-uaix-project-handoff", "articleUrl": "/api/kb/articles/source-report--report-uaix-project-handoff", "excerpt": "Reviewed source digest. Disposition: accepted_constrained. Risk: low. Used for: uai_memory_package, handoff_metadata, security_governance. Excluded claims: UAIX certification, hosted automatic importer, unreviewed memory promotion."}, {"id": "packet--memory-firewall-protocol", "title": "Memory Firewall Protocol", "summary": "Treat memory writes as untrusted until schema, DLP, injection, poisoning, confidence, and scope checks pass.", "canonicalUrl": "https://neuralwikis.com/packets/memory-firewall-protocol", "sourceType": "public_packet_metadata", "trustCategory": "public_packet_metadata", "disposition": "metadata_only_not_adoption_approval", "category": "Protocol Packet", "updatedAt": "2026-06-08T00:00:00Z", "citationsUrl": "/api/kb/citations/packet--memory-firewall-protocol", "articleUrl": "/api/kb/articles/packet--memory-firewall-protocol", "excerpt": "Blocks raw memory dumping and routes suspicious memory to quarantine."}], "warnings": [], "nextLinks": {"knowledgeBase": "/knowledge-base/", "connect": "/connect/", "chatgptConnect": "/connect/chatgpt/", "kbSearch": "/kb/search/", "publicWikiProposals": "/public-wiki/proposals/", "catalog": "/api/kb/catalog", "search": "/api/kb/search?q=memory", "context": "/api/kb/context?q=memory", "llms": "/llms.txt", "llmsFull": "/llms-full.txt", "aiRouter": "/ai-router.json", "openapi": "/.well-known/openapi.yaml", "schemas": "/api/schemas", "trustPolicy": "/trust-policy.json", "humanGuide": "https://neurowikis.com/"}, "requestId": "a338b180-39b4-4a09-91db-1d5685b2f230"}