Recall relevant knowledge by ranked keyword and semantic (hybrid) relevance. Returns ranked results with heading, snippet, matched terms, level, parent, and sectionType. Sections from the same document receive a sibling score boost when multiple sections match. Use multiple short keyword queries for best coverage. Use recall for full content. A retrieval_verdict of "unanswered" means kbdb does not have it: investigate, do not guess.

Store durable knowledge in the agent's second brain. Store decisions, corrections, and facts that cost real effort to find. Do not store what the code or docs already say, chat summaries, guesses, or secrets. When a stored fact is wrong, fix it with revise, not a second copy. Structured content (Markdown, HTML, TOML) splits into sections sharing a docid, each carrying a level and a parent. Attach tags for scoping. replace matches on title within its document and heading path; a title with neither matches on title alone, so name things distinctly.

Remove a section from the knowledge base by its kb-id, or an entire document (and its member sections) by docid.

Low-level fetch of a section or document by identifier. For AI agent workflows, prefer recall which includes metadata, context, and back-references.

Expand remembered context after search. Retrieves full content and context for sections by identifier, returning section text, level, parent, metadata, references, and back-references. Call it on the kbids search returned. Use maxTokens to bound the payload, and format: compact when you only need the content.

Get knowledge base status including document count, section count, index size, and cache statistics.

Compose a rendered Markdown document from one or more kbid or docid identifiers.

Verify the integrity of the knowledge base. Reports checksum mismatches, orphan sections, broken references, and circular reference chains.

Remove unreferenced sections from the knowledge base. A section is eligible when no document manifest references it.

Reconstruct all index files from section files and document manifests on disk. Use this to recover from index corruption.

Export the knowledge base as a self-contained directory snapshot (sections, documents, catalog -- no indexes).

Shorthand for learn with sectionType: skill. Skills are prompt templates; use {{argName}} placeholders for arguments. Deprecated; removal in 2.0.0.

Shorthand for search with sectionType: skill. Deprecated; removal in 2.0.0.

Shorthand for unlearn with sectionType: skill. Deprecated; removal in 2.0.0.

Shorthand for recall with sectionType: skill. Deprecated; removal in 2.0.0.

Shorthand for content with sectionType: skill. Deprecated; removal in 2.0.0.

Shorthand for learn with sectionType: agent. The content is the persona text. Deprecated; removal in 2.0.0.

Shorthand for search with sectionType: agent. Deprecated; removal in 2.0.0.

Shorthand for unlearn with sectionType: agent. Deprecated; removal in 2.0.0.

Shorthand for recall with sectionType: agent. Deprecated; removal in 2.0.0.

Shorthand for content with sectionType: agent. Deprecated; removal in 2.0.0.

Propose knowledge for storage and let the user confirm it, when the host supports elicitation.

Validate and persist retrieval eval cases drafted via the eval-generate prompt. Rejects cases whose kbids do not resolve, and drops duplicates. Call it only with kbids a search actually returned; invented ids fail the whole batch.

When a stored fact is wrong, fix it with revise, not a second copy. Content addressing means the correction gets a NEW kb-id. The old one is retired, not deleted: it stops appearing in search, still reads by kb-id, and "history" walks between them. Fields you omit keep their existing values.

List every revision of a section, oldest first, and name the current one. Call it when a kb-id you hold no longer appears in search: revisions are retired, not deleted, so a stale kb-id still leads to the text that replaced it. A section revised once has two revisions; one never revised has one.

List what relates to a section and HOW, so you can decide what to read next. Eight relations: supersedes, superseded-by, parent, child, sibling, references, referenced-by, similar. Seven are recorded facts; only "similar" is inferred from a cosine. Related is not relevant -- judge these against your task.

Propose groups of stored sections that could become one, so a knowledge base of twenty overlapping notes can become a few good ones. Proposes ONLY -- nothing is merged. Each group reports its weakest link. Without an entailment judge kbdb CANNOT tell whether a group disagrees with itself; read every section before merging it.

Report pairs of stored sections covering the same ground, to read together before trusting either. Similarity finds pairs; it cannot judge agreement. Without an entailment model every pair reads "related", and no "contradicts" means nothing was asked, not that nothing conflicts.

Report what this knowledge base is repeatedly asked and answers badly, worst first. Call it to decide what to learn next. Ranking is triage, not measurement: the log records how each search went, never whether the answer helped.

Record whether a recalled section answered a query. Accumulates real usage into an eval dataset. Call it once you know whether a result helped, including when it did not -- a wrong answer is the more useful judgement.