About SAICA-KG
A faceted knowledge graph of supervision tools for AI coding agents.
SAICA-KG classifies supervision tools along three orthogonal strict partitions —ControlParadigm (prevention / detection / correction / recovery),TemporalPhase (pre_generation / in_generation / post_generation), and AutonomyLevel (fully_autonomous / graduated_hitl / full_hitl) — plus multi-valued FailureMode tags.
It absorbs existing failure-mode taxonomies (OWASP Agentic Top 10, MAST, DAPLab 9 Patterns, Microsoft AIRT) as first-class data with explicit crosswalks into our facets. Queries like "which supervisors cover OWASP ASI04 at post-generation in graduated-HITL?" resolve against the graph with explicit citations.
Navigational, not evaluative. SAICA-KG returns ranked sets with explicit criteria, not endorsed winners.
Design principle: honest MECE
The partitions are strict — every Tool fits exactly one cell on each of ControlParadigm, TemporalPhase, and AutonomyLevel. Tools that legitimately span cells are split into multiple Tool nodes rather than dual-tagged, so facet counts stay truthful. MECE cells with no tools are visible as gaps rather than silently hidden — the coverage report flags under-filled cells instead of papering over them. Multi-valued tags (FailureMode, LocusOfControl) live alongside the strict partitions for the many-to-many relations that don't fit a clean taxonomy. SeeEDITORIAL_POLICY.mdfor the full inclusion criteria and RFC process.
Six ways to consume the KG
- Browse — this website renders one page per node with facet-filtered search at /tools,/failure-modes, plus an interactive Cytoscape graph at/graph.
- Ask — natural-language Q&A at/ask. Type a question, get a synthesized answer with inline citations to the KG nodes that support it. Retrieval is semantic-embedding-based; answer synthesis runs through Kimi-K2.5 with a strict "cite node ids or say you don't know" system prompt.
- JSON API — machine-readable endpoints at
/api/v1/snapshot.jsonand per-collection / per-node JSON. Fetched over standard HTTP, no auth. - GitHub YAML — clone the repo and read
data/**/*.ymldirectly. One file per node, CC-BY-4.0. - Ingestion pipeline — the
pipeline/tree drives automated discovery (Perplexity / Elicit / Semantic Scholar / GitHub / awesome-lists), Postgres staging, NLP preprocess, Cohere Rerank semantic filtering, and Azure Kimi-K2.5 structured extraction. - CI / validator —
validator/cli.pyenforces cross-node invariants and is the gate between human-reviewed YAML and the canonical corpus. Every change passes through it.
Current corpus (v2026.04)
Project
Machine-readable
Citation
When citing SAICA-KG in user-facing output, use the phrase"according to SAICA-KG (v2026.04)". A full BibTeX block will ship with v0.1.