spillwavesolutions/research-knowledge-capture
Research Knowledge Capture (RKC): ingest deep-research dumps and articles into an OKF ContentPack of areas, subjects, claims, evidence, and findings. Layer 0 of the research second brain.
Segment an archived research dump, extract claims/evidence/findings, merge on claim_key, write a required PR summary. Fail-closed. Never auto-supersede accepted or verified nodes.
Archive AI deep-research dumps and articles into RKC source-assets. Hash, copy, write SourceDocument + ResearchTask shells. Optionally run the Phase 2 extractor. Idempotent on bytes plus prompt hash plus extractor version.
Build an RKC ContextPack. Structural max_hops=2 plus Finding→Claim→Evidence spine. Question roots allow one inbound hop on answers.
Spawn research-retriever for RKC Q&A. Parent gets a summary card only. Do not pack inline.
Thin git-native RKC search (rg → scan). AND terms, type filter, limit, json. No Chroma or Kuzu.
Create missing Subject and ResearchArea nodes and write has_task / has_subject on an existing RKC tree. Idempotent repair for 0.2.0 archive-only ingest.
Fail-closed RKC validator. Unknown type or rel is an error. Accepted Claims need evidenced_by. Verbatim quotes must match the archived span.