List accessible vaults as {name, description} pairs. Response is slim — no metadata (id/role/created_at) — to fit large tenants in agent context. Returns {vaults, total, returned, truncated?, hint?}. Optional args:

• filter: substring match on name+description (case-insensitive). Use to narrow to a domain (e.g. filter='finance').

• limit / offset: pagination when there are many matches.

• include_archived: include archived vaults (default false).

Create a new knowledge base vault (a separate, access-controlled repository for documents). Pass external_git to instead create a read-only mirror of an upstream git repo — the vault tracks the remote on a polling schedule and rejects user writes.

Store a new document. The response carries the canonical uri (akb://{vault}/doc/{path}) — use that to address the document from every other tool. Automatically chunked and indexed for semantic search.

Retrieve a document by its URI. Returns full content with metadata. Use akb_browse or akb_search first to obtain the URI. Optionally pass a commit hash (from akb_history) to read a previous version.

Update an existing document. Only provide fields you want to change.

Edit a single document by replacing exact text. Scope is one document. old_string must be unique within the document (or use replace_all). If old_string is not found or appears multiple times, the call fails with a clear error. For find-and-replace across many documents, use akb_grep with replace instead.

Delete a document. Removes from Git, search index, and knowledge graph.

Browse ALL vault content — documents (by collection), tables, and files. Without collection: shows top-level collections, tables, and files. With collection: shows documents and files in that collection. Response is slim by default (no summary field) so large vaults (70+ collections) fit in the agent's context window. Returns {vault, path, items, total, returned, truncated?, hint?}. Use filter to narrow when you know a domain keyword. Each item carries its canonical uri.

Search documents with hybrid retrieval — dense vector (semantic) fused with BM25 sparse (keyword) via Reciprocal Rank Fusion. Handles both natural-language questions and short keyword queries well. For exact string / regex matches (code, URLs, version numbers) prefer akb_grep. Returns each hit's uri; use akb_drill_down or akb_get with that URI for full content. Response reports returned (in results) and total_matches (size of the deduped prefetch pool — NOT a corpus-wide hit count; vector ANN is top-K only). When truncated=true the prefetch pool was capped, meaning the corpus may hold more hits than reported — switch to akb_grep with count_only=true for an exact literal-substring count, or refine the query.

Search for exact text or regex patterns across document content. Unlike akb_search (semantic/meaning-based), this finds exact string matches — use it for specific terms, URLs, code snippets, version numbers, etc. Returns matching documents (each with its uri) and matched lines. Optionally pass replace to find-and-replace across all matching documents. Three response shapes (mutually exclusive): default lines, count_only=true (grep -c — per-doc counts + total, no snippets), files_with_matches=true (grep -l — just the URIs that contain the pattern). The default shape always reports BOTH returned_* (what fit under limit) and total_* (full corpus matches) plus a truncated flag — if truncated, switch to count_only/files_with_matches for the full picture instead of bumping limit.

Read section-level (L3) content of a document, or list its section headings. Two modes:

• mode='sections' (default): return body content of matched sections. Filter with section (heading substring) and/or pattern (substring grep on body). On empty match the response carries an outline so you can retry.

• mode='outline': return heading paths only (no bodies). Use this to discover the document's structure cheaply before deciding which section to read. Returns {uri, sections|outline, returned, total?, truncated?, hint?}.

Get activity history for a vault — who changed what, when, and why. Returns Git commit history with changed file list. Use akb_diff to see the actual content changes for a specific commit.

Get the content diff for a document at a specific commit. Shows what was added/removed/modified. Use akb_history or akb_activity to find commit hashes first.

Get relations for any resource (document, table, or file). Shows cross-type connections: doc→table, doc→file, table→file, etc.

Get a knowledge graph — nodes (documents, tables, files) and edges (relations). Provide uri to get a subgraph centered on any resource with BFS traversal. Provide vault (without uri) to get the full vault graph.

Create a relation between any two resources (documents, tables, files). Source and target are AKB URIs. Relation types: depends_on, related_to, implements, references, attached_to, derived_from. Example: link a design doc to its data table, or attach a diagram file to a spec.

Remove a relation between two resources. If relation type is omitted, removes ALL relations between the two resources.

Get provenance for a document — who created it, when, which entities were extracted.

Create a structured data table in a vault. The response carries the canonical uri (akb://{vault}/table/{name}). Tables live alongside documents inside collections and follow the same permissions. Define columns with name and type (text, number, boolean, date, json). Optional collection (e.g. 'sessions/learnings') groups the table under that collection so it appears beside the documents and files there in akb_browse; omit for vault root.

Execute SQL on vault tables. Tables are real PostgreSQL tables. Use table names directly (e.g. 'pipeline', 'partners') — they are auto-resolved to the vault's tables. For cross-vault queries, list all vaults in the vaults parameter. Prefix table names with vault name for cross-vault: sales__pipeline, external_projects__partners. SELECT requires reader role. INSERT/UPDATE/DELETE requires writer role.

Permanently delete a table and all its rows. Cannot be undone. Requires admin role on the vault.

Modify a table's schema — add, remove, or rename columns via ALTER TABLE DDL. Requires admin role.

Store something in your persistent memory. Memories persist across sessions — use this to remember important context, decisions, preferences, or learnings for future sessions. Categories: context (current work), preference (how you like to work), learning (things you learned), work (completed work), general.

Retrieve your persistent memories from previous sessions. Call this at the start of a session to recall what you were working on. Filter by category for specific types of memory.

Delete a specific memory by its ID.

Create a public share URL for a document, table query, or file. For a document or file, pass the resource uri. For a table query, pass the SQL plus vault (queries can span multiple vaults — list them in query_vault_names). Supports expiration, password protection, view count limits, snapshots, and section filtering. Returns a shareable URL accessible without authentication. Prefer public_url_full (absolute URL) when sharing the link with a user; fall back to public_url (relative path) only if public_url_full is null.

Remove a public share. Pass slug to delete a single publication, or uri to delete all publications for that resource.

List all publications in a vault (documents, table queries, files).

Create a snapshot of a table_query publication. Saves the current query result to S3 and switches mode to 'snapshot'.

Get detailed vault information: owner, member count, document/table/file/edge counts, last activity.

List all members of a vault with their roles (owner, admin, writer, reader).

Grant vault access to a user. You must be owner or admin of the vault.

Revoke a user's vault access. You must be owner or admin.

Search for users by username, display name, or email. Use this to find users before granting vault access.

Get your current profile — username, email, display name, role. Use this to check who you are authenticated as.

Transfer vault ownership to another user. Only the current owner can do this.

Archive a vault (makes it read-only). Only the owner can do this.

Permanently delete a vault and ALL its data — documents, chunks, tables, files, edges, Git repo. This cannot be undone. Owner or admin only.

Create an empty collection (folder) inside a vault. Idempotent — returns {created: false} if the collection already exists. Writer or higher role.

Delete a collection. If empty, removes the metadata row. If non-empty, requires recursive=true to cascade delete every document and file under the path. Cascade emits one git commit for the entire batch. Writer or higher role.

Set vault public access level. Owner only. 'none'=private, 'reader'=public read, 'writer'=public read+write.

Get version history of a document — who changed it, when, and why. Each entry is a Git commit. Use the commit hash with akb_get to read a previous version.

Get help on AKB tools and workflows. Call with no arguments for an overview. Drill down into categories or specific tools for details and examples. START HERE if you're new to AKB.

Upload a local file to a vault's file storage (S3-backed). Use for PDFs, images, datasets, or any binary content too large for akb_put. Response includes the canonical uri — akb://{vault}/coll/{collection}/file/{uuid} when stored under a collection, or akb://{vault}/file/{uuid} at the vault root — pass that to akb_get_file / akb_delete_file. MIME type is auto-detected from the filename extension unless overridden.

Download a file from vault storage to a local path. Pass the file URI — akb://{vault}[/coll/{coll_path}]/file/{uuid} — from akb_browse or akb_put_file.

Delete a file from vault storage by its URI.