Enables AI agents to discover formal concepts, inspect structured dialectical disputes, locate verified bibliographic evidence with chapter coordinates and fair-use excerpts, and cryptographically verify citations using SHA-256 hashes and Ed25519 receipts, including through a built-in offline canon sandbox.
Enables AI clients to search a personal corpus, read relevant source passages, and answer questions with traceable evidence from imported sessions, notes, and articles.
Enables language models to verify claims against a local document corpus by returning a literal supporting quote, a contradiction, or an explicit refusal when evidence is insufficient. Runs deterministically offline over local sources without network access or LLM calls.
Exposes seven read-only tools that let an existing chat model search a private, incrementally ingested PDF library, fetch full parent sections with provenance and hash validation, check evidence completeness, audit literal quote anchors, view original PDF pages, and explore a frozen citation snapshot. It provides source-first retrieval and provenance without invoking another model or certifying scientific conclusions.
Enables coding agents to analyze a repository evidence-first, answering questions as verifiable claims with source evidence, targeted test observations, and reference resolution.