Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NODE_ENVNoThe environment the server is running in.development
POSTGRES_DBYesPostgreSQL database name.agi_db
POSTGRES_HOSTYesPostgreSQL host address.localhost
POSTGRES_PORTYesPostgreSQL port.5432
POSTGRES_USERYesPostgreSQL user name.agi_user
POSTGRES_PASSWORDYesPostgreSQL password.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
create_memoryC

Create a new memory with optional type-specific metadata

search_memories_similarityC

Search memories by vector similarity

search_memories_textC

Search memories by text content using full-text search

get_memoryB

Retrieve a specific memory by ID and mark it as accessed

get_memory_clustersC

Retrieve memory clusters ordered by importance/activity

activate_clusterC

Activate a memory cluster and get its associated memories

create_memory_clusterC

Create a new memory cluster

get_identity_coreB

Retrieve the current identity model and core memory clusters

get_worldviewC

Retrieve current worldview primitives and beliefs

get_memory_healthB

Get overall statistics about memory system health

get_active_themesC

Get recently activated memory themes and patterns

create_memory_relationshipC

Create a relationship between two memories

get_memory_relationshipsC

Get relationships for a specific memory

find_related_memoriesC

Find memories related through graph traversal

consolidate_working_memoryC

Consolidate multiple working memories into a single semantic memory

archive_old_memoriesC

Archive old memories based on age and importance criteria

prune_memoriesC

Permanently delete memories based on criteria

get_cluster_insightsC

Get detailed analytics for a memory cluster

find_similar_clustersC

Find clusters similar to a given cluster

create_working_memoryC

Create a temporary working memory with expiration

get_working_memoriesC

Retrieve current working memories

cleanup_expired_working_memoryC

Clean up expired working memories

get_memory_historyC

Get change history for a specific memory

search_memories_advancedC

Advanced memory search with multiple criteria

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.2/5.0

Scored across 24 tools

Disambiguation4/5

Most tools have distinct purposes, but some overlap exists in search functionality (search_memories_advanced, search_memories_similarity, search_memories_text) which could cause confusion about which to use for different query types. The memory retrieval tools (get_memory, get_memory_clusters, get_working_memories) are well differentiated by their specific targets.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case throughout, such as 'activate_cluster', 'create_memory', and 'get_memory_health'. This predictability makes the tool set easy to navigate and understand at a glance.

Tool Count3/5

With 24 tools, the count feels heavy for a memory management system, bordering on excessive. While the domain is complex, some tools could potentially be consolidated (e.g., the three search variants) to reduce cognitive load without losing functionality.

Completeness5/5

The tool set provides comprehensive coverage for memory lifecycle management, including creation, retrieval, search, relationships, clustering, maintenance (cleanup, archive, prune), and analytics (health, insights, themes). No obvious gaps are present for the stated AGI memory domain.

Maintenance

ActivityInactive
ResponsivenessSyncing