Skip to main content
Glama
Neboy72

Nexus Memory

by Neboy72
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

remember

Persist AI agent memories across sessions by storing categorized facts, preferences, and rules with scopes and provenance tracking for reliable recall.

Instructions

Store a memory for AI agents. Persists information across sessions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesThe memory content to store
scopeNoOptional project/agent area label ([a-z0-9-], max 40 chars). Scoped memories are excluded from OTHER agents' auto-prefetch (only the agent whose NEXUS_SCOPE matches sees them automatically); explicit recall() always finds them. Omit or 'default' = visible to every agent's auto-prefetch.default
sourceNoWhere this memory came from (e.g. 'conversation', 'document', 'cron')
categoryYesMemory category (state-prefixing scope): fact, belief, session, rule, preference, temp. Required for state-prefixing — the server applies 'fact' as a backward-compatible default when the client omits this field.fact
confidenceNoOptional: Confidence score (0.0-1.0) attached to the provenance. Use 0.9+ for verified facts, 0.5-0.8 for beliefs/inferences, <0.5 for speculative notes. The server applies a sensible default (0.7) when omitted.
source_urlNoRecommended: URL or origin reference for provenance tracking. When set, the server activates Justification-Check (Rung 2) on recall: the URL is checked via async HTTP HEAD and the result is returned as `verification` (`verified`, `unreachable`). Optional — omit to skip verification (the memory will be returned with `verification: "unchecked"` on recall).
access_levelNoWho can see this: public (all agents), trusted (approved agents), private (only owner)public
effective_fromNoOptional ISO-8601 date/datetime: when this fact became valid (temporal validity). Defaults to now. Use for retro-dated imports (e.g. mail import with the original mail date).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.18.7
    • addedInput schema / properties / scope
      Added value: +{
+  "default": "default",
+  "description": "Optional project/agent area label ([a-z0-9-], max 40 chars). Scoped memories are excluded from OTHER agents' auto-prefetch (only the agent whose NEXUS_SCOPE matches sees them automatically); explicit recall() always finds them. Omit or 'default' = visible to every agent's auto-prefetch.",
+  "type": "string"
+}
  2. Changed1 schema field changedv0.16.0
    • addedInput schema / properties / effective_from
      Added value: +{
+  "default": null,
+  "description": "Optional ISO-8601 date/datetime: when this fact became valid (temporal validity). Defaults to now. Use for retro-dated imports (e.g. mail import with the original mail date).",
+  "type": "string"
+}
  3. First observedv0.13.1

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the burden. It discloses persistence across sessions, which is a key behavioral trait. However, it doesn't mention side effects like overwriting existing memories, deduplication, or that scoped memories are excluded from other agents' auto-prefetch (though the schema covers scope semantics). The description adds some value but not deep behavioral context.

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?

Two short sentences, front-loaded with the core action. No wasted words. It could add a bit more context, but it's appropriately concise.

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

Completeness3/5

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

For a write tool with 8 parameters and no output schema, the description is minimal. The schema covers parameters, but the description doesn't explain return behavior, error cases, or how this interacts with recall/forget. Given the tool's complexity (8 params, scoping, provenance), a bit more context would help, but the schema fills many gaps.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all 8 parameters thoroughly. The description adds no parameter-level meaning beyond 'store a memory'. Baseline 3 is appropriate since the schema does the heavy lifting.

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

Purpose4/5

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

The description states a clear verb and resource: 'Store a memory for AI agents. Persists information across sessions.' This distinguishes it from recall/forget siblings. However, it doesn't explicitly contrast with update or fact_history, so it's clear but not fully differentiated.

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

Usage Guidelines3/5

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

The description implies usage: use this to persist information across sessions. It doesn't explicitly state when to use this vs recall/forget/update, nor when not to use it. The schema provides some context (e.g., scope affects auto-prefetch), but the description itself lacks explicit routing guidance.

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