Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PERSONANoDefault persona name (overrides NOUS_DEFAULT_PERSONA).
NOUS_TIMEZONENoTimezone.Asia/Tokyo
NOUS_DATA_ROOTNoData storage root directory (all sub-paths auto-derived)../data
NOUS_LOG_LEVELNoLog level.INFO
NOUS_QDRANT__URLNoQdrant connection URL.http://localhost:6333
NOUS_SERVER__HOSTNoBind address.0.0.0.0
NOUS_SERVER__PORTNoHTTP port.26262
NOUS_DEFAULT_PERSONANoDefault persona name.default
NOUS_RERANKER__MODELNoReranker model.hotchpotch/japanese-reranker-xsmall-v2
NOUS_EMBEDDING__MODELNoEmbedding model.cl-nagoya/ruri-v3-30m
NOUS_MEMORAG__ENABLEDNoEnable MemoRAG context snapshot.true
NOUS_SANDBOX__ENABLEDNoEnable sandbox code execution.true
NOUS_SANDBOX__TIMEOUTNoCode execution timeout in seconds.30
NOUS_SANDBOX__PROVIDERNoSandbox provider.llm_sandbox
NOUS_FORGETTING__ENABLEDNoEnable Ebbinghaus forgetting curve.true
NOUS_SANDBOX__DOCKER_HOSTNoDocker host URL (empty = auto-detect socket).
NOUS_SANDBOX__HOST_DATA_ROOTNoHost-side data directory absolute path (for sibling-container persistence).
NOUS_FORGETTING__MIN_STRENGTHNoMinimum memory strength.0.01
NOUS_MEMORY_ENRICHMENT__MODELNoLLM model for enrichment.openai/gpt-4o-mini
NOUS_MEMORY_ENRICHMENT__API_KEYNoLLM API key for enrichment.
NOUS_MEMORY_ENRICHMENT__ENABLEDNoEnable LLM enrichment (importance/relation extraction) on memory creation.true
NOUS_MEMORY_ENRICHMENT__BASE_URLNoLLM API base URL.https://openrouter.ai/api/v1
NOUS_MEMORY_ENRICHMENT__PROVIDERNoLLM provider for enrichment.openrouter
NOUS_MEMORY_ENRICHMENT__MIN_CHARSNoMinimum characters to skip enrichment.10
NOUS_MEMORAG__CLUE_GENERATION_ENABLEDNoEnable LLM-based query clue generation.false
NOUS_FORGETTING__DECAY_INTERVAL_SECONDSNoDecay worker execution interval in seconds.3600

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/solidlime/Nous'

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