Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_URLNoFull API Endpoint for the LLM strategy (e.g., http://localhost:11434/api/generate).http://localhost:11434
USE_WORKERNoRun Archivist in a background thread to prevent blocking. Options: true, false.true
MEMORY_DB_PATHNoLocation of the SQLite database file../memory.db
EXTENSIONS_PATHNoOptional path to load custom tool extensions from external directory. Allows adding private/experimental tools without modifying the codebase.
TAG_MATCH_BOOSTNoScore boost for exact tag matches in recall results. Higher = stronger tag priority.0.15
ARCHIVIST_LANGUAGENoOptional language setting for the Archivist. Default is 'en'.en
ARCHIVIST_STRATEGYNoControl automatic entity extraction behavior. Options: passive, nlp, llm. Can be comma-separated (e.g., nlp,llm).nlp
CONTEXT_TODO_LIMITNoMax pending todos shown in memory://current-context.3
CONTEXT_MAX_ENTITIESNoMax high-importance entities in context.5
CONTEXT_MAX_MEMORIESNoMax recent memories in context.5
CONTEXT_WINDOW_LIMITNoMax characters returned by memory://current-context.500
EMBEDDING_CONCURRENCYNoMax concurrent embedding operations for remember_facts. Higher values = faster batch processing but more CPU/memory usage.5
MEMORY_HALF_LIFE_WEEKSNoWeeks until memory importance decays to 50%. Longer = slower decay.4.0
MEMORY_SEMANTIC_WEIGHTNoBalance between semantic similarity (0.7) and decayed importance (0.3) in recall ranking.0.7
ENABLE_CONSOLIDATE_TOOLNoEnable the consolidate_context tool for retrospective memory extraction. Options: true, false.false
EXTRACT_COMPLEX_CONCEPTSNoEnable extraction of modifier+noun phrases (e.g., 'optimized WGSL'). Options: true, false.true
MEMORY_CONSOLIDATION_FACTORNoStrength of access-based consolidation. Higher = frequently-used memories resist decay more.1.0

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Beledarian/mcp-local-memory'

If you have feedback or need assistance with the MCP directory API, please join our Discord server