[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E0VC18NMP1QBSRJ3TPQ7MB":3,"skill-same:01M7E0VC18NMP1QBSRJ3TPQ7MB":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7E0VC18NMP1QBSRJ3TPQ7MB","graphiti-zep-memory-governor",null,"Govern bi-temporal knowledge graphs with Graphiti future-edge clamping, MinHash\u002FLSH entity dedup, RRF\u002FMMR reranking, and Zep typed ontologies. Do not use for static SQL joins or generic web crawling.","SpectreDeath\u002FBrain-Harness","SpectreDeath","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F207463416?v=4","01M7AVGR1D4X8ADT47APKGVH2Z","JL","01M7AVGR2HSGD23BA5DBTJJTVN",0,"MIT","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: graphiti-zep-memory-governor\ndescription: Govern bi-temporal knowledge graphs with Graphiti future-edge clamping, MinHash\u002FLSH entity dedup, RRF\u002FMMR reranking, and Zep typed ontologies. Do not use for static SQL joins or generic web crawling.\n---\n\n# Graphiti Zep Memory Governor\n\n`graphiti-zep-memory-governor` distills Graphiti bi-temporal edge normalization and contradiction invalidation, entropy-gated 32-perm MinHash\u002FLSH entity deduplication and dangling endpoint cleanup, RRF\u002FMMR\u002Fshortest-hop hybrid search reranking, weighted label-propagation clustering with per-group sequential queues, and Zep typed ontology compilation from `getzep\u002Fgraphiti` (`ed231965`) and `getzep\u002Fzep-python` (`305d8b3a`).\n\nSee [CARD.md](CARD.md) for the companion summary card, pipeline stages, and mandatory invariants checklist.\nConsult [config.default.yaml](config.default.yaml) for baseline entropy, LSH, RRF\u002FMMR, and wire property defaults.\n\n---\n\n## 1. Bi-Temporal Edge Normalization & Contradiction Resolution\n\nSeparate system ingestion timelines from real-world event truth intervals without corrupting future commitments:\n\n1. **Clamp Future Assertions & Filter Soft Deadlines (`normalize_bitemporal_edges`)**: Detect planned\u002Fscheduled assertions (`_FUTURE_ASSERTION_RE`), clamp `valid_at > reference_time` back to `reference_time`, and clear false `invalid_at > reference_time` caused by target deadlines (`_DEADLINE_RE` absent `_ONGOING_STATE_END_RE`).\n2. **Preserve Contradiction Audit Trails**: Record contradicted edge UUIDs alongside surviving facts so historical states remain queryable at earlier points in time.\n\n> **Completion criterion**: `BiTemporalEdgeNormalizationReport` normalizes event validity timestamps and partitions contradicted vs surviving edges cleanly.\n\n---\n\n## 2. Entropy-Gated MinHash\u002FLSH Dedup & Dangling Endpoint Hygiene\n\nEliminate false fuzzy merges on short acronyms while pruning unreferenced synthetic endpoints:\n\n1. **Gate MinHash\u002FLSH Behind Character Shannon Entropy (`resolve_entities_and_endpoints`)**: Defer names below `NAME_ENTROPY_THRESHOLD = 1.5` or shorter than `6` chars with `\u003C 2` tokens to LLM disambiguation; match high-entropy 3-gram shingles via `32`-perm 64-bit `blake2b` MinHash, `4`-band LSH, and `>= 0.9` Jaccard similarity with label promotion (`Entity` first).\n2. **Materialize & Prune Dangling Endpoints**: Synthesize missing edge endpoints transiently and garbage-collect any materialized endpoints absent from `kept_edge_endpoints`.\n\n> **Completion criterion**: `EntityDedupResolutionReport` separates deterministic MinHash\u002FLSH merges from low-entropy LLM deferrals and reports surviving vs pruned endpoints.\n\n---\n\n## 3. Hybrid Reranking, Community Clustering & Typed Ontologies\n\nFuse multi-signal retrieval, detect weighted communities, and validate typed memory schemas:\n\n1. **Rerank Sparse, Dense & Graph Candidates (`rerank_hybrid_results`)**: Fuse multi-source lists via `rrf` (`rank_const = 1`), diversify normalized vectors with `mmr` (`lambda = 0.5`), or rank local neighborhoods with `node_distance` (`center_node` distance `0.1`, unreachable `inf`).\n2. **Cluster Communities & Compile Typed Ontologies (`cluster_communities_and_compile_ontology`)**: Run edge-weighted label propagation (`candidate_rank > 1`), verify non-empty `group_id` sequential queue assignment, and compile `EntityModel`\u002F`EdgeModel` schemas across `text`\u002F`int`\u002F`float`\u002F`boolean` while forbidding `Identity` fields on edges.\n\n> **Completion criterion**: `HybridRerankReport` and `CommunityAndOntologyReport` produce deterministic rankings, communities, and schema validation diagnostics.\n\n---\n\n## The Three Foundational Pillars\n\n### 1. Bi-Temporal Timeline Separation with Future-Commitment Clamping\nMaintain independent ingestion and world-validity intervals while preventing soft delivery deadlines from falsely invalidating planned assertions.\n\n### 2. Specificity-Gated LSH Deduplication & Endpoint Garbage Collection\nGate probabilistic MinHash\u002FLSH entity merging on character Shannon entropy and prune transiently materialized edge endpoints that lose surviving graph edges.\n\n### 3. Multi-Signal Retrieval Fusion & Typed Group-Serialized Memory\nCombine RRF, normalized MMR, and hop-distance reranking atop per-group serialized graph writes and strictly described entity\u002Fedge ontologies.\n\n---\n\n## Anti-Patterns\n\n- **Soft Deadlines Written as `invalid_at`** — Saving target dates like \"due by Friday\" as `invalid_at` without ongoing state-end markers falsely expires active commitments.\n- **Unconditional Fuzzy Merging on Low-Entropy Names** — Running 3-gram Jaccard or MinHash matching on short or repetitive identifiers merges unrelated concepts instead of deferring to LLM resolution.\n- **Leaking Materialized Dangling Endpoints** — Persisting synthetic placeholder nodes created for edges that are later dropped during filtering pollutes the entity graph.\n- **Attaching `Identity` Properties to Edges or Empty Docstrings** — Assigning entity deduplication `Identity` markers to `EdgeModel` fields or omitting type\u002Ffield descriptions degrades extraction and breaks Zep ontology compilation.\n","# Graphiti Zep Memory Governor\n\n`graphiti-zep-memory-governor` distills Graphiti bi-temporal edge normalization and contradiction invalidation, entropy-gated 32-perm MinHash\u002FLSH entity deduplication and dangling endpoint cleanup, RRF\u002FMMR\u002Fshortest-hop hybrid search reranking, weighted label-propagation clustering with per-group sequential queues, and Zep typed ontology compilation from `getzep\u002Fgraphiti` (`ed231965`) and `getzep\u002Fzep-python` (`305d8b3a`).\n\nSee [CARD.md](CARD.md) for the companion summary card, pipeline stages, and mandatory invariants checklist.\nConsult [config.default.yaml](config.default.yaml) for baseline entropy, LSH, RRF\u002FMMR, and wire property defaults.\n\n---\n\n## 1. Bi-Temporal Edge Normalization & Contradiction Resolution\n\nSeparate system ingestion timelines from real-world event truth intervals without corrupting future commitments:\n\n1. **Clamp Future Assertions & Filter Soft Deadlines (`normalize_bitemporal_edges`)**: Detect planned\u002Fscheduled assertions (`_FUTURE_ASSERTION_RE`), clamp `valid_at > reference_time` back to `reference_time`, and clear false `invalid_at > reference_time` caused by target deadlines (`_DEADLINE_RE` absent `_ONGOING_STATE_END_RE`).\n2. **Preserve Contradiction Audit Trails**: Record contradicted edge UUIDs alongside surviving facts so historical states remain queryable at earlier points in time.\n\n> **Completion criterion**: `BiTemporalEdgeNormalizationReport` normalizes event validity timestamps and partitions contradicted vs surviving edges cleanly.\n\n---\n\n## 2. Entropy-Gated MinHash\u002FLSH Dedup & Dangling Endpoint Hygiene\n\nEliminate false fuzzy merges on short acronyms while pruning unreferenced synthetic endpoints:\n\n1. **Gate MinHash\u002FLSH Behind Character Shannon Entropy (`resolve_entities_and_endpoints`)**: Defer names below `NAME_ENTROPY_THRESHOLD = 1.5` or shorter than `6` chars with `\u003C 2` tokens to LLM disambiguation; match high-entropy 3-gram shingles via `32`-perm 64-bit `blake2b` MinHash, `4`-band LSH, and `>= 0.9` Jaccard similarity with label promotion (`Entity` first).\n2. **Materialize & Prune Dangling Endpoints**: Synthesize missing edge endpoints transiently and garbage-collect any materialized endpoints absent from `kept_edge_endpoints`.\n\n> **Completion criterion**: `EntityDedupResolutionReport` separates deterministic MinHash\u002FLSH merges from low-entropy LLM deferrals and reports surviving vs pruned endpoints.\n\n---\n\n## 3. Hybrid Reranking, Community Clustering & Typed Ontologies\n\nFuse multi-signal retrieval, detect weighted communities, and validate typed memory schemas:\n\n1. **Rerank Sparse, Dense & Graph Candidates (`rerank_hybrid_results`)**: Fuse multi-source lists via `rrf` (`rank_const = 1`), diversify normalized vectors with `mmr` (`lambda = 0.5`), or rank local neighborhoods with `node_distance` (`center_node` distance `0.1`, unreachable `inf`).\n2. **Cluster Communities & Compile Typed Ontologies (`cluster_communities_and_compile_ontology`)**: Run edge-weighted label propagation (`candidate_rank > 1`), verify non-empty `group_id` sequential queue assignment, and compile `EntityModel`\u002F`EdgeModel` schemas across `text`\u002F`int`\u002F`float`\u002F`boolean` while forbidding `Identity` fields on edges.\n\n> **Completion criterion**: `HybridRerankReport` and `CommunityAndOntologyReport` produce deterministic rankings, communities, and schema validation diagnostics.\n\n---\n\n## The Three Foundational Pillars\n\n### 1. Bi-Temporal Timeline Separation with Future-Commitment Clamping\nMaintain independent ingestion and world-validity intervals while preventing soft delivery deadlines from falsely invalidating planned assertions.\n\n### 2. Specificity-Gated LSH Deduplication & Endpoint Garbage Collection\nGate probabilistic MinHash\u002FLSH entity merging on character Shannon entropy and prune transiently materialized edge endpoints that lose surviving graph edges.\n\n### 3. Multi-Signal Retrieval Fusion & Typed Group-Serialized Memory\nCombine RRF, normalized MMR, and hop-distance reranking atop per-group serialized graph writes and strictly described entity\u002Fedge ontologies.\n\n---\n\n## Anti-Patterns\n\n- **Soft Deadlines Written as `invalid_at`** — Saving target dates like \"due by Friday\" as `invalid_at` without ongoing state-end markers falsely expires active commitments.\n- **Unconditional Fuzzy Merging on Low-Entropy Names** — Running 3-gram Jaccard or MinHash matching on short or repetitive identifiers merges unrelated concepts instead of deferring to LLM resolution.\n- **Leaking Materialized Dangling Endpoints** — Persisting synthetic placeholder nodes created for edges that are later dropped during filtering pollutes the entity graph.\n- **Attaching `Identity` Properties to Edges or Empty Docstrings** — Assigning entity deduplication `Identity` markers to `EdgeModel` fields or omitting type\u002Ffield descriptions degrades extraction and breaks Zep ontology compilation.\n",{"name":5,"description":7},"main","6b1c31fc13f2ca7fd9930d7c1c40aecbd3cc63bc",".agents\u002Fskills\u002Fgraphiti-zep-memory-governor","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness","https:\u002F\u002Fgithub.com\u002FSpectreDeath","I'm here to manage stress so I wouldn't expect earth shattering break throughs I'm just an enthusiast that likes making stuff. ","2026-11-15 05:32:58",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add SpectreDeath\u002FBrain-Harness --skill graphiti-zep-memory-governor",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill graphiti-zep-memory-governor",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill graphiti-zep-memory-governor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002FSKILL.md",true,[45,51,55,61],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",2668,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",504,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002Fconfig.default.yaml",{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Fgraphiti_zep_memory_engine.py","SCRIPT","脚本",4521,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002Fscripts\u002Fgraphiti_zep_memory_engine.py",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"tests\u002Ftest_graphiti_zep_skill_contracts.py",2453,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002Ftests\u002Ftest_graphiti_zep_skill_contracts.py",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7E0W6FR68J2N9CXCZTAQJFX","ui-behavior-primitive-architect","Architect, audit, and verify zero-dependency headless UI behavior primitives, WebMCP agent bridges, WAI-ARIA\u002FSSR\u002FRTL tri-modal checks, and framework expert routing. Do not use for static CSS theme styling or backend database migrations.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fui-behavior-primitive-architect\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7E0VZ7JQNW34G271DENFGYP","trustgraph-ontology-governor","Govern knowledge graphs, SHACL-AF triple policies, OntologyRAG subclass validation, PROV-O dual named graphs, and Laya entropy decision scoring. Do not use for relational SQL queries or generic web scraping.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftrustgraph-ontology-governor\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7E0VQ6Z7R45Q8QAZ4MT39EK","shim-harness-governor","Govern universal CLI agent loops, 4-tier tool permissions, ancestor-symlink workspace sandboxes, deterministic-first command routing, collision-safe MCP namespacing, and layered skill loading. Do not use for static UI styling or external SQL analytics.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshim-harness-governor\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7E0V12ABE1RW3ZRCST8VH5Z","agora-mcp-workbench-architect","Architect, audit, and orchestrate Agora Workbench MCP servers, loopback sidecars, unified state graphs, gateway\u002Fdispatcher connectors, and policy-enforced data lakes. Do not use for static frontend CSS styling or non-MCP desktop GUI automation.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagora-mcp-workbench-architect\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7BFYG6QT3484VC57TZ19V7P","skill-eval-assurance-runner","Evaluate and assure agent skills using small-N Wilson confidence intervals, unbiased pass^k reliability, deterministic trajectory graders, preflight boundary honesty, and sealed digest verification. Do not use for subjective prose review or unconstrained production deployment.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-eval-assurance-runner\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7AWC435PHN9H6M22JPZ6HKN","ontology-spider","Query, traverse, validate, and explain Brain Harness knowledge vaults and domain ontologies using formal logic reasoning. Do not use for fuzzy text search or ungrounded vector clustering.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002Fplugins\u002Fmemory_and_epistemics\u002Fontology_spider\u002FSKILL.md",[],[]]