Understand this story
Dario Pasquini has open-sourced iKnow, a local viewing tool for inspecting the personal knowledge graph in macOS 26. According to a popular Hacker News post, Pasquini reverse-engineered the personal knowledge graph built by the two daemons knowledgeconstructiond and intelligenceplatformd, finding that the data is stored in 51 SQLite databases under ~/Library/IntelligencePlatform, with the core graph.db using a triple structure of 181 entity classes and 278 predicates. Kinship relations are inferred by two XGBoost classifiers based on 144 features, 84 of which come from photos in which people co-occur; the results are written to a separate entityTagging.db and recomputed daily. The post also notes that deleted records enter the expired_stable_graph table, so conclusions may outlast the evidence. The tool is currently public alongside the analysis.
AI-generated from public reports
Developments
1 confirmed developments
Dario Pasquini open-sources iKnow to view the Mac personal knowledge graph
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 28
Hacker News Trending
Researcher reverse-engineers Apple's personal knowledge graph: 181 entity classes, 278 predicates, and 144-dimensional kinship inference features
The researcher conducted a reverse analysis of the personal knowledge graph built by the two daemons knowledgeconstructiond and intelligenceplatformd in macOS 26, finding that its data is stored in 51 SQLite databases under ~/Library/IntelligencePlatform, with the core graph.db using a triple structure of 181 entity classes and 278 predicates. Kinship relationships are inferred by two XGBoost classifiers based on 144 features, of which 84 features come from co-occurring photos; the results are written to a separate entityTagging.db and recalculated daily. The author also open-sourced a local viewing tool, iKnow, and pointed out that deleted records enter the expired_stable_graph table, so conclusions may outlast the evidence.