ModelBrain exposes a small, fixed surface to your assistant over MCP: fourteen tools. Four handle remembering, recalling, correcting and forgetting; one lists memories without a query; six organize memories into partitions; three are read-only health checks. Everything that manages the installation stays on the command line.
Looking for platforms, price, hardware needs and what leaves your computer in one place? Fact sheet →
Pick macOS, Windows or Linux, and see how each one connects to your assistants.
Read the guide →Aider has no MCP command. What that means, and what to do instead.
Read the guide →Choose Connect to ChatGPT in the menu, add ModelBrain as a plugin in ChatGPT, then sign in and pick the computer.
Read the guide →Turn on sharing in the menu, add a custom connector in Grok with the relay URL, then sign in and pick the computer. New.
Read the guide →Every item in the menu bar and system tray menu, and what it does.
Read the guide →The Allow or Block prompt, forget limits, undo, client tokens, and what client identity does not protect against.
Read the guide →Sync between computers, backups, ChatGPT, billing, cancelling and deleting.
Read the guide →Share a partition with your team: invitations, roles, access, single sign-on and billing.
Read the guide →Copy-paste project instructions and ten tips for steady recall and saving.
Read the tips →What gets read, what's excluded automatically, and how to remove one.
Read the guide →Write your memories to plain Markdown or JSON Lines files, or search them from a terminal.
Read the guide →Add your Obsidian vault folder and get answers that cite your notes. No plugin.
Read the guide →What it does differently from plain search, and what it costs.
Read the guide →object_type, tags, relations to existing memories, and supersedes to replace an older one instead of duplicating it. Marking it inferred keeps it out of default results until reviewed.reasoning_statusrevert by default: revert tombstones the current version and brings the one before it back; chain removes a memory's whole correction history; object removes just the one version named. A connector-synced chunk ignores the mode and forgets its whole source, marked so it is never re-ingested automatically.current resolves to it. Per connection: a new connection has no partition chosen, so it saves into unsorted and searches every active partition until it calls this or is bound by a .modelbrain.toml, --partition or MODELBRAIN_PARTITION.Reverting to an earlier version is forget's own revert mode, the default; see what a forget call actually has to guarantee.
text (required, up to 64 KB), tags, partition, inferred, object_type (free text: architecture_decision/pitfall/convention/verified_command are meaningful conventions, not a fixed enum), relations (edges to existing keys), supersedes (the key this corrects), similar_min_relevance (0.0 to 1.0, how close an existing memory must be to be listed as similar). Returns a key.
query (required), k (1–50, a hard limit; a value outside that range is rejected, not silently clamped), min_relevance, scope (all/user/connectors/connector:<id>), tags, partition_scope (current/all/all_active/id:<ulid>/a partition name), reasoning, widen, verify. Since 0.6: collapse_sources (default true: repeated chunks of one synced file fold into the best chunk; false returns every chunk), dedupe_identical, object_type (one value or a list), created_after and created_before (the first must be earlier than the second), folder, branch_scope (default current), as_of. Hits no longer carry score or pending.
key (required), mode (revert by default, undoing the last correction), chain (tombstone the whole correction history), or object (tombstone just this one). Idempotent: forgetting something already gone isn't an error.
key (required), edges (include linked memories, default false), history (walk the correction chain backward, default false). piece_only (return just the matching piece of a long memory). Text is cut at 64 KB. Returns found: false rather than erroring on an unknown or forgotten key.
scope (all/user/connectors), tags, limit (1–50, default 20), newest_first, after_key with the returned next_cursor to page, partition_scope, branch_scope, object_type, created_after, created_before. Lists what is stored without searching.
days (1–90, default 7), sessions (0–50, default 10). Which assistants used ModelBrain, how often, and what they saved or recalled.
A connection that has not picked a partition saves into unsorted and searches every active partition. partition_use, a .modelbrain.toml in the project, --partition or MODELBRAIN_PARTITION bind it to one partition for both saving and searching, the same as recall's partition_scope default. all_active reads every active partition at once and overrides that binding.
recall called with reasoning on either returns a verified answer or a reasoning_unavailable object naming why, never a guess it couldn't check. Full explanations, in plain language: troubleshooting.
A rejected call returns one of these in its error data, not just a message string, so a client can branch on it programmatically.
invalid_params · invalid_key · empty_text · text_too_long · invalid_tag · invalid_scope · invalid_forget_mode · invalid_partition_target · context_window_exceeded · relation_target_not_found · supersedes_conflict · pending_conflict · reserved_partition_name · duplicate_partition_name · partition_not_found · default_partition_immutable · cross_partition_edge · embedding_failed · storage_io · store_corrupt · recovery_required · store_locked · usage_log_unavailable · busy · internal · store_busy · relay_scope · rate_limited · client_token_required · client_rate_limited · client_blocked
These manage the installation itself, not a single conversation, so they stay on the command line rather than something an assistant could be talked into calling mid-chat.
Which folders and sources feed the vault.
Manual snapshot and recovery of the local vault.
Storage-tier maintenance: compaction, tier migration.
Leaving should be as plain as arriving. Uninstalling is one command, it tells you exactly what it is about to remove, and it does not touch your memories unless you ask it to.
Stops ModelBrain, removes the program and the entry it added to Claude Desktop's settings. Your vault folder is left where it is, and its path is printed. On Linux, run ~/.local/lib/modelbrain/uninstall.sh.
Your vault is ordinary files in one folder, so deleting that folder removes everything. On Linux, uninstall.sh --purge-data does it for you. There is nothing to request from us for the free local tier.
Stop the daemon, delete the vault folder (its location is on the install page for your system), and remove the ModelBrain line from your assistant's MCP settings. The vault is ordinary files, so deleting the folder is complete deletion, with nothing left to ask us for.
If you used sync, managed backup or Teams, uninstalling the software does not cancel the subscription or delete what we hold; cancel from your account, and server-held copies are deleted 30 days after the paid period ends, as the terms describe.
How the four storage tiers, the daemon and your assistant fit together.
Read the architecture →