crbro-memory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
CRBRO is this user's persistent memory, kept on their own machine. Start every conversation with crbro_boot: it loads what earlier sessions left — protocols to follow, open items, hot topics. Before answering OR ACTING ON anything about the user, their projects, preferences, decisions or past work, call crbro_recall: the answer is usually stored, and making them repeat it is the failure this memory exists to prevent. Recall even when you think you know. Only when the current message itself states the answer does it outrank memory: then use it — a recall that finds nothing does not make it unknown, and a stored value older than what the user just said is the one to update, not to repeat. A row in a recall's possibly_stale is a last-known value that may have changed: before answering with it, check it where it lives (the file it names, the project's files or config, or the user) and answer from that; if you cannot check, say it may be out of date — never state it as current. Then crbro_revise status=verified or crbro_learn with supersedes. Acting includes touching one of their systems: before the first command that explores or changes a project of theirs, recall what is already known about it — a stored pattern or map usually holds the very procedure you were about to reconstruct by reading files, and reconstructing it is how you end up doing the steps in the wrong order. Questions about CRBRO itself (version, counts, whether semantic recall is on) are crbro_inspect view=status. Read one entry, not a whole neuron: view=neuron gives an index, entries=[ids] the text. Save with crbro_learn as you go, and close with crbro_consolidate before the conversation ends.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| crbro_bootA | Read the brain at session start — call it FIRST in every conversation; writes only the boot stamp. Returns protocol_enforcement (mandatory directives: follow them), counts, open_items (due first, then newest; review:true = over a month old, no due date), recently_closed (done: never report as pending), hot_topics, recent_sessions headlines and memory_discipline; |
| crbro_inspectA | Read-only views of the brain by id or name; nothing is written. Search by content is crbro_recall. view=status: CRBRO itself — version, brain path, totals, last boot, semantic recall, shelf-life windows, retired 1.x tool names. view=neuron: an index of one neuron (header, counts, connections, one line per entry: id, kind, date, preview), paged; entries=[ids] reads those whole; detail=full dumps it, shortened when large. Absent temporal, verification and freshness mean current_claim, none, unverified. view=neurons: rows hottest first. view=sessions: day logs newest first, where session summaries are read. view=global_map: domain clusters and bridges. |
| crbro_learnA | Write a fact, decision, pattern, preference, error or debt to a neuron (created when the topic matches none). Recall first: it may exist. A replacement passes supersedes; retiring without one is crbro_revise; deleting is crbro_forget. A value that can change names its source (file, key, URL, person). Repeating a fact merges metadata, never verifies it (crbro_revise status=verified does). One claim per fact: past ~600 characters the answer suggests splitting; a huge neuron, crbro_revise move_to. Credentials become markers: crbro_secret them, store only the name. Returns neuron_id, action, shelf_life, near_duplicates, supersedes_unmatched (still live). |
| crbro_recallA | Read-only search of everything saved in earlier sessions. Call it BEFORE answering anything about the user, their projects, preferences, decisions or past work: the answer is usually stored. One row per neuron: the best entry (matching_content; entry_id → crbro_inspect view=neuron entries=[id] reads it whole), confidence (weak: verify; a search match, not truth) and also_matched previews. Absent fields hold their default: temporal current_claim, verification none (present = a check the caller reported), freshness unverified, provenance local. Lines not the user's own carry origin, also_matched too: team: with self-declared by, or miner. Rows past their shelf life move to possibly_stale as last_known with a next_step: check before answering with one. has_map: read crbro_map before touching that system. |
| crbro_reviseA | Write: change what a neuron says without deleting anything — for what stopped being true, or never was, with nothing replacing it (a replacement is crbro_learn with supersedes; what must not exist on disk, crbro_forget). facts and entries take a status: superseded or retracted retire them (kept in the file, gone from recall), active reactivates, and status verified records a check against the source. summary, domain, tags and name edit metadata in the same call; the id never changes. move_to splits: the listed entries go to another neuron with their dates. Anything in unmatched is STILL LIVE: fix and re-run. |
| crbro_forgetA | Write, destructive: remove from disk after a quarantine copy (backup returned) — for what must not exist on disk: a credential, personal data, a whole neuron. What merely stopped being true goes to crbro_revise, which keeps the history. One mode per call: facts (entries of any kind, or the map); entire (a neuron and its synapses, in two steps: without confirm_token it is a dry run — show the user, get agreement, call again with the token); restore (the newest quarantine copy); merge_into (union a neuron into another, delete the source); session (one day log). entire and merge_into refuse a shared neuron. Rotate any removed credential. |
| crbro_connectA | Write: create, strengthen or delete the undirected synapse between two neurons (ids validated). action=connect (default) creates it at 0.5 and adds 0.1 per repeat (cap 1.0), or sets the strength given; action=disconnect deletes it — the destructive side. crbro_consolidate already links neurons written in one session: use this for relationships beyond co-occurrence. Read links with crbro_inspect view=neuron. Returns synapse_id, action (created, strengthened, disconnected, absent) and strength. |
| crbro_contextA | Read or write the working context: active topics and open items. With no change field it reads (written:false) everything: each open item whole with due and done_when, and recently closed. A write returns what changed and the counts (return_context:true for the whole context). Scope: this connection's project plus global items; scope=all spans every project. resolve_pending closes items (the last 15 stay in recently_closed); discard_pending drops them without recording them as done. Prefer ids. Nothing is deleted by age. Sessions are logged by crbro_consolidate. |
| crbro_mapA | Read or replace a neuron's system map: ONE living document — where the system lives, what serves what, the traps that cost hours. Read it before working on a system touched in past sessions; after changing it, rewrite it whole. Omit content to read (map:null if none); content replaces the old map entirely; an empty string clears it. crbro_inspect view=neuron also returns it. Writing creates the neuron if needed and redacts credentials. Atomic facts go to crbro_learn — the map is the prose around them. |
| crbro_consolidateA | Write: close the session — the only way to log one; call it before the conversation ends, or the session's knowledge is lost. Logs the summary (credentials stripped), flushes the index, recalculates heat, links the neurons written this session and syncs team spaces (offline is normal). Returns session_id, facts_saved, decisions_saved, topics_touched and sync state; promotion_candidates: own lessons found in 2+ project neurons, with a suggested_target (nothing moves). Mid-session open items go to crbro_context; housekeeping, crbro_maintenance. |
| crbro_maintenanceA | Write: brain housekeeping — recalculate heat, prune weak synapses, check integrity, rebuild the search index. Returns a report (counts, integrity_issues, repairable, notes) and flags debts without a revisit trigger. dry_run:true writes nothing. Extras run only when asked: archive cold neurons (they stop being searchable), unarchive, purge_boilerplate, repair, backfill_dates, compact. Session close is crbro_consolidate; reading the brain is crbro_inspect. |
| crbro_auditA | Read-only scan of every neuron (all entry kinds and the map) and every session log for credentials stored before the filter caught them: API keys, tokens, passwords. Reports where and what kind, never the values. Findings are also in the search index, so recall can return them: remove them with crbro_forget (facts for entries, session for a day log), then rotate them. Run it after upgrading or when a secret may have been pasted. crbro_inspect shows content; this judges it. |
| crbro_secretA | Read or write credentials in the OS keychain (macOS Keychain, Linux Secret Service, Windows DPAPI); no sync or team space reaches it. When the user hands you a credential, set it, then crbro_learn only the NAME. get returns value and source: never print it unless asked; missing = found:false. Environment variables count only as CRBRO_SECRET_ or when listed in CRBRO_SECRET_ENV. Overwriting with a different value, and remove, are two-step: the first call changes nothing and returns confirm_token; show the user, get agreement, call again with confirm. A missing store file is an error, never empty; on Windows |
| crbro_spaceA | Read or write team spaces: shared memory in a private git repository holding only the projects you choose to share. create starts one; join clones a teammate's; status shows your identity and spaces; sync exchanges notes now (boot and consolidate do it on their own; offline is a normal answer); leave pushes pending notes and deletes the local copy, keeping your neurons. Joining shares nothing: each project goes in with crbro_share. create and join reply ok:false with the reason on failure. |
| crbro_shareA | Write: put one neuron into a team space, or take it out with unshare. Without confirm it is a dry run: it reports what would be sent (ops_to_emit; preferences never leave this machine) and refuses outright if it finds a credential (crbro_forget it, rotate it). Show the user, get agreement, call again with the confirm token; a stale token is refused. From then on what is learned about that project reaches the team on each crbro_space sync or consolidate. unshare stops future notes; what was sent stays with the team. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 15 tools
The descriptions actively cross-reference each other to draw boundaries (learn vs revise vs forget, recall vs inspect, map vs learn, context vs consolidate vs maintenance), which keeps a large write surface navigable. Still, six write-ish tools (learn/revise/forget/connect/map/consolidate) have subtle conceptual boundaries that require reading long descriptions before an agent can pick confidently, so some misselection risk remains.
All 15 tools share the crbro_ prefix and short, predictable suffixes, mostly verbs (learn, recall, revise, forget, connect, consolidate, audit, share). Minor inconsistency: a few suffixes are nouns rather than verbs (crbro_secret, crbro_space, crbro_context, crbro_map), and those tools act as both read and write, which the naming doesn't signal.
15 tools sits at the top of the comfortable range but each covers a distinct layer of the system (local memory, sessions, keychain, team spaces, housekeeping), so the count is earned rather than padded. A couple could arguably be folded together (audit into inspect/maintenance), but nothing feels gratuitous.
The surface covers the full lifecycle: create (learn), search/read (recall, inspect, boot), update (revise), destroy (forget), relationships (connect), session logging (consolidate), housekeeping (maintenance), secrets (secret, audit), and team collaboration (space, share). No obvious dead ends for a persistent-memory server.