Garry's Opinionated OpenClaw/Hermes Agent Brain
TypeScript
/**
* Top-level `gbrain` / `gbrain --help` usage text. Engine-free and import-light
* so src/cli.ts can answer it on the fast path without loading the dispatcher
* (src/cli/main.ts), which prints the same text on its own `--help` route.
*/
import { VERSION } from '../version.ts';
export function printHelp() {
console.log(`gbrain ${VERSION} -- personal knowledge brain
USAGE
gbrain <command> [options]
SETUP
mcp grant <name> --help Grant hosted access; private credential handoff
mcp verify --help Verify connection, permissions, and memory
setup claude-code|codex [--dry-run]
Give an agent memory: brain + MCP + hooks, verified (--remove undoes)
init [--pglite|--supabase|--url] Create brain (PGLite default, no server)
init --prefer-postgres [--allow-docker]
Postgres-first install ladder (env URL >
Supabase token > local PG > docker > PGLite)
engine status [--json] [--probe] Which engine + URL source, engine-free
db-repair [--yes] [--json] Diagnose/fix Postgres access, engine-free
(--yes --apply-rewrites for config rewrites)
migrate --to <postgres|pglite> Move the brain between engines (PGLite -> Postgres graduates: plan, then --yes --expect)
migrate embeddings --to <p:model> Re-embed onto another embedding provider
embeddings enable --embedding-model <p:model> Turn on embeddings in place (keeps pages/facts)
embeddings prewarm [--dry-run] Load the vector indexes into shared_buffers when they fit (Postgres)
upgrade Self-update
check-update [--json] Check for new versions
repair [<kind>] [--apply] Preview/apply residual repairs (timeline, visibility, safe-chunks)
projections drain [--limit n] Rebuild queued text projections now [--json]
doctor [--json] [--fast] [--probe-pglite] Health check (resolver, skills, pgvector, RLS, embeddings; --probe-pglite runs the scratch-store probe)
integrations [subcommand] Manage integration recipes (senses + reflexes)
MEMORY (facts agents recall; MEMORY_VERBS v1)
remember "<fact>" --entity <slug> Save a fact the user stated, with --provenance; world-visible
facts are pushed into new agent sessions (private: recall only)
recall [<entity>] [--query <q>] Find saved facts
forget <fact-id> Withdraw a fact
PAGES
get <slug> Read a page
put <slug> [< file.md] Write/update a page
delete <slug> Delete a page
list [--type T] [--tag T] [--limit N]
List pages
find <glob|prefix|name> [--type T] [--source S] [--limit N]
Find pages by slug, path or title
SEARCH
search <query> Keyword search (tsvector)
query <question> [--expand] Hybrid search (RRF; expansion per search mode)
ask <question> [--expand] Alias for query
IMPORT/EXPORT
import <dir> [--no-embed] Import markdown directory
sync [--repo <path>] [flags] Git-to-brain incremental sync
sync --watch [--interval N] Continuous sync (loops until stopped)
See also: autopilot --install (continuous daemon).
sync --all --missing-path skip Classify sources whose local_path is absent
on this machine as skipped, not failed
export [--source <id>] [--dir <p>] Coherent Markdown snapshot; fresh output, no overwrite
export --restore-only [--repo <p>] Restore missing db_only files; export --help for safe retry
[--type T] [--slug-prefix S] With optional filters
FILES
files list [slug] List stored files
files upload <file> --page <slug> Upload file to storage
files upload-raw <file> --page <s> Smart upload (size routing + .redirect.yaml)
files signed-url <path> Generate signed URL (1-hour)
files sync <dir> Bulk upload directory
files verify Verify all uploads
EMBEDDINGS
embed [<slug>|--all|--stale] Generate/refresh embeddings
LINKS
link <from> <to> Create typed link (alias: link-add)
[--link-type T] [--link-source S] provenance defaults to 'manual'
unlink <from> <to> Remove link (alias: link-rm)
[--link-type T] [--link-source S] filter which edges to remove
link-sources List provenances in use, with edge counts
backlinks <slug> Incoming links
graph <slug> [--depth N] Traverse link graph (nodes locally; remote MCP defaults to bidirectional edges)
graph-query <slug> [--type T] Edge-based traversal with type/direction filters
[--depth N] [--direction in|out|both]
TAGS
tags <slug> List tags
tag <slug> <tag> Add tag
untag <slug> <tag> Remove tag
TIMELINE
timeline [<slug>] View timeline
timeline-add <slug> <date> <text> Add timeline entry
TOOLS
extract <links|timeline|all> Extract links/timeline (idempotent)
[--source fs|db] [--source-id ID] [--dir <brain>]
[--type T] [--since DATE] [--include-frontmatter]
[--workers N|--concurrency N] [--dry-run] [--json]
extract links --by-mention [--ner] --source db
extract timeline --from-meetings [--infer-dates] --source db
extract --stale [--source-id ID] [--catch-up] [--dry-run] [--json]
extract links --source db --repair-attendance --source-id ID
[--limit 250] [--after-slug SLUG] [--json]
Apply: --apply-preview FILE --confirm DIGEST --yes --backup-verified --checkpoint FILE
extract --explain <kind> [--json] Full details: gbrain extract --help
publish <page.md> [--password] Shareable HTML (strips private data, optional AES-256)
check-backlinks <check|fix> [dir] Find/fix missing back-links across brain
lint <dir|file> [--fix] Catch LLM artifacts, placeholder dates, bad frontmatter
backfill <kind|list> v0.30.1: run a registered backfill (effective-date, ...)
orphans [--json] [--count] Find pages with no inbound wikilinks
beliefs <enable|status|...> Belief ledger coverage: enable, disable, status, reconcile, backfill
salience [--days N] [--kind P] v0.29: pages ranked by emotional + activity salience
anomalies [--since D] [--sigma N] v0.29: cohort-based statistical anomalies (tag, type)
feedback <status|reset> retrieval feedback: learned page weights; rate answers with gbrain rate
transcripts <ingest|status|recent> v0.46: import agent session logs + chat exports (local-only)
dream [--dry-run] [--json] Run the overnight maintenance cycle once (cron-friendly).
See also: autopilot --install (continuous daemon).
compile-context --target <t> Compile a deterministic, scanned, budgeted context
[--budget N] [--check] file (claude-code | codex | openclaw)
decide <status|probe|enable|...> System One decision support (Jev); every slot off by default
memory-proposals list|show|approve|deny QM's proposed timeline entries and links awaiting your decision
facts relink [--dry-run] Link facts saved without an entity to the entity they name
check-resolvable [--json] [--fix] Validate skill tree (reachability/MECE/DRY)
report --type <name> --content ... Save timestamped report to brain/reports/
questions pin|list|status|refresh|unpin Pinned questions: cited answers kept current (owner-private)
OPEN LOOPS (Gmail/Calendar/Contacts connector — v0.47)
google setup [--account <email>] One command: BYO OAuth → source → first sync → first digest
google connect|status|disconnect Connect/inspect/remove a Google account (idempotent; --json)
waiting [--top N] [--json] Who is waiting on you, what you promised, context to respond
loops list|show|done|drop|mute Inspect and manage open loops (mute sender <email>)
core list|show|status|add|remove Always-loaded core memory (also diff|ack|init|suggest)
creds list|remove|export|import Generic credential vault (redacted output; encrypted bundles)
BRAIN (capture / ideate / explore — v0.37/v0.38)
capture [content] [--file PATH] Single entrypoint for getting content into the brain (a page;
a fact to recall later is \`remember\`)
[--stdin] [--slug s] [--type t] Inline content / file / stdin; writes to inbox/ by default
[--source ID] [--quiet|--json] Multi-source brains: route to a non-default source
brainstorm <question> [--json] Bisociation idea generator (hybrid search + far-set + judge)
[--save|--no-save] [--limit N]
lsd <question> [--json] Lateral Synaptic Drift: inverted-judge brainstorm
[--save|--no-save] [--limit N] rewarding far-from-obvious + axiomatic inversions
think "<question>" [--anchor <s>] Multi-hop cited synthesis across pages + takes + graph
[--save] [--source <id>] Full flags: gbrain think --help
SOURCES (multi-repo / multi-brain)
sources list Show registered sources
sources add <id> --path <p> Register a source (id = short name, e.g. 'wiki')
sources remove <id> Remove a source + its pages (--confirm-destructive)
sources archive <id> Soft-delete: hide from search, recoverable for 72h
sources restore <id> Un-archive a soft-deleted source
sources archived List soft-deleted sources and their purge expiry
sources purge [<id>] Permanently delete archived sources
sources status Per-source dashboard (sync lag, embed coverage)
guests init [--writer <w>] [--yes] Set up a guest source for outside guests' notes
sources --help Full subcommand list (rename, default, attach,
current, federate, set-cr-mode, webhook, harden, ...)
sync --all Sync all sources with a local_path
sync --source <id> Sync one specific source
git commit-push -m <m> -- <paths> Commit + push only those paths in a shared checkout
(lock, in-memory merge, no rebase/stash); --pull, --push-only
repos ... DEPRECATED alias for 'sources' (v0.19.0)
CODE INDEXING (v0.19.0 / v0.20.0 Cathedral II)
code-def <symbol> [--lang l] Find the definition of a symbol across code pages
code-refs <symbol> [--lang l] Find all references to a symbol (JSON-first)
code-callers <symbol> Who calls this symbol? (v0.20.0 A1)
code-callees <symbol> What does this symbol call? (v0.20.0 A1)
query <q> --lang <l> Filter hybrid search to one language (v0.20.0)
query <q> --symbol-kind <k> Filter to symbol type (function|class|method|...) (v0.20.0)
reconcile-links [--source id] [--dry-run] Batch-recompute doc↔impl edges in one source
reindex-code [--source id] [--yes] [--force] Explicit code-page reindex (v0.20.0; --force re-chunks unchanged pages)
reindex-search-vector [--dry-run] [--yes] [--json]
Recreate FTS triggers + backfill under
$GBRAIN_FTS_LANGUAGE (default 'english')
sync --strategy code Sync code files into the brain
JOBS (Minions)
jobs submit <name> [--params JSON] Submit background job [--follow] [--dry-run]
jobs list [--status S] [--limit N] List jobs [--json]
jobs get <id> [--json] Job details + history
jobs cancel <id> Cancel job
jobs retry <id> Re-queue failed/dead job
jobs prune [--older-than 30d] Clean old jobs
jobs stats [--json] Job health dashboard
jobs watch [--follow] Live queue dashboard
jobs work [--queue Q] Start worker daemon (Postgres only)
jobs supervisor [start|status|stop] Auto-restarting worker wrapper
ADMIN
stats Brain statistics
stats --by source,type [--since 30d] [--collapse-aliases]
Live page counts per source and type
health Brain health dashboard
history <slug> [--json] Page version history
revert <slug> <version-id> Revert to version
features [--json] [--auto-fix] Scan usage + recommend unused features
autopilot [--repo] [--interval N] Self-maintaining brain daemon
config [show|get|set] <key> [val] Brain config
pricing [set|list|unset] <model> Register model prices for cost caps (host only)
protocol [conformance|stats] MEMORY_VERBS v1: schemas, conformance
certification, local usage stats + TTHW
storage status [--repo <path>] Storage tier status and health
[--json] (git-tracked vs supabase-only)
serve MCP server (stdio)
--surface verbs|starter|full Tool surface: the 7 memory verbs, the ~20-op
starter set, or every op (default full).
On --http this is the per-client CEILING.
--advertise verbs|starter|full List only this surface in tools/list (plus
request_tools); the rest stays callable.
--access read-only|full stdio: list and dispatch only read operations
serve --http [--port N] HTTP MCP server with OAuth 2.1
--token-ttl N Access token TTL in seconds, 60-7776000 (default: 3600)
--enable-dcr Enable Dynamic Client Registration (DCR clients default to authorization_code)
--enable-dcr-insecure Also allow the consent-bypassing client_credentials grant on DCR (implies --enable-dcr)
--public-url URL Public issuer URL (required behind proxy/tunnel)
connect <mcp-url> --token <t> Wire Claude Code to a remote gbrain (bearer token)
[--install] [--json] Print the paste-ready command, or --install to run it
auth <create|list|revoke|...> Manage legacy tokens + OAuth 2.1 clients
auth --help Full subcommand list (register-client,
rescope, rescope-client, rescope-token, revoke-client, ...)
watch [--json] Push-based context: pipe conversation turns in,
volunteered brain pages stream out (#2095)
call <tool> '<json>' Raw tool invocation
version Version info
--tools-json Tool discovery (JSON)
Run gbrain <command> --help for command-specific help.
`);
}