Skip to main content
Glama
Sign In
crbro-memory

crbro-memory

by Octonove
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Boot the brain

crbro_boot
Idempotent

Read the brain at session start — call it FIRST in every conversation, before any other work; writes only the boot stamp (and the brain itself on first use).

Instructions

Read the brain at session start — call it FIRST in every conversation, before any other work; writes only the boot stamp (and the brain itself on first use). Loads memory from earlier sessions: hot topics, active context with open_items and recently_closed (never report recently_closed as pending; verify open_items before repeating them), recent_sessions, counts, active protocols as a protocol_enforcement block you must follow, memory_discipline (the rules for using this memory well) and retired_tools (old tool names → their replacement). Readies the search index and syncs shared team spaces (offline is normal). Pass project (the working folder or repo name) to put that project's neurons first: project_neurons. Skipping it loses all context; close the session with crbro_consolidate.

Input Schema

NameRequiredDescriptionDefault
projectNoWorking folder or repository. Full paths identify distinct projects, even with the same folder name. Existing aliases resolve to one stable project; this connection keeps its own scope.
project_idNoOptional stable local project id when declaring aliases; never use a credential.
project_aliasesNoOther folders/remotes explicitly belonging to this project. No remote access is performed.
project_neuronsNoExisting neuron ids to bind to this project. Replaces the binding; omitted preserves it. Suggested name matches are not an explicit binding.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.10.0
    • changedInput schema / properties / project / description
      Previous value: -"The folder or repository this session works in: a path (\"C:/code/crbro-memory\"), a repo name or a remote (\"owner/repo\"); only the last segment counts. Neurons whose name, system map or fact keywords name it come first in hot_topics and are listed in project_neurons (at most 5). Omit it and boot is exactly as without."New value: +"Working folder or repository. Full paths identify distinct projects, even with the same folder name. Existing aliases resolve to one stable project; this connection keeps its own scope."
    • addedInput schema / properties / project_aliases
      Added value: +{
+  "description": "Other folders/remotes explicitly belonging to this project. No remote access is performed.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 31,
+  "type": "array"
+}
    • addedInput schema / properties / project_id
      Added value: +{
+  "description": "Optional stable local project id when declaring aliases; never use a credential.",
+  "type": "string"
+}
    • addedInput schema / properties / project_neurons
      Added value: +{
+  "description": "Existing neuron ids to bind to this project. Replaces the binding; omitted preserves it. Suggested name matches are not an explicit binding.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 100,
+  "type": "array"
+}
  2. Changed1 schema field changedv2.9.1
    • addedInput schema / properties / project
      Added value: +{
+  "description": "The folder or repository this session works in: a path (\"C:/code/crbro-memory\"), a repo name or a remote (\"owner/repo\"); only the last segment counts. Neurons whose name, system map or fact keywords name it come first in hot_topics and are listed in project_neurons (at most 5). Omit it and boot is exactly as without.",
+  "type": "string"
+}
  3. Changed1 schema field changedv2.4.0
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  4. First observedv1.4.0

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Explains the write behavior that justifies readOnlyHint=false ('writes only the boot stamp... and the brain itself on first use'), discloses that offline is normal (relevant to openWorldHint), and spells out operational rules like following the protocol_enforcement block and not reporting recently_closed as pending. This goes well beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the session-start directive and the write caveat before enumerating payload contents. It is dense and a bit run-on, but nearly every clause carries actionable instruction rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even without an output schema, the description enumerates the returned payload (hot topics, active context, recent_sessions, counts, protocols, memory_discipline, retired_tools) and the caveats for using it. Nothing material is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds behavioral meaning for project ('put that project's neurons first: project_neurons'). The remaining parameters (project_id, project_aliases) get no narrative explanation, but their schema descriptions are thorough.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read the brain at session start') and explicitly positions it as the first call of every conversation. An agent can distinguish it from crbro_recall, crbro_learn, and crbro_context without inspecting schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to call it FIRST before any other work, warns that skipping it loses all context, and pairs it with a closing step ('close the session with crbro_consolidate'). It also names the alternative flow implicitly by contrasting with session-end behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools