Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_HOSTNoOllama endpoint; used first if reachablehttp://localhost:11434
ENGRAM_DB_PATHNoSQLite database location
ENGRAM_DATA_DIRNoRoot for database, archive, and logs
ENGRAM_LOGS_DIRNoLog directory
ENGRAM_MCP_HOSTNoBind address. Anything but loopback is refused unless ENGRAM_MCP_TOKEN is set127.0.0.1
ENGRAM_MCP_TOKENNoWhen set, /mcp requires Authorization: Bearer <token> (401 otherwise); /health stays open for supervisors. Required before the daemon will bind anything but loopback
ANTHROPIC_API_KEYNoEnables the Anthropic provider (final tier of the LLM cascade)
ENGRAM_ARCHIVE_DIRNoConversation archive directory
ENGRAM_LOCAL_MODELNoOllama model name (must be pulled on the Ollama host)qwen2.5:7b
OPENROUTER_API_KEYNoEnables the OpenRouter provider
ENGRAM_HTTP_WORKERSNoWorker count in HTTP mode (0 = run tool calls inline on the main thread)2
ENGRAM_OPENAI_MODELNoModel served by that route; setting it activates the `openai` tier
ENGRAM_LLM_PROVIDERSNoTier order, comma-separated. A tier left out is never tried; unknown names are ignored with a warningollama,openai,openrouter,anthropic
ENGRAM_EMBEDDING_DIMSNoMatryoshka embedding dimensions (must match the existing DB)256
ENGRAM_LLM_TIMEOUT_MSNoPer-request timeout for every tier. Raise it for a slow local model120000
ENGRAM_MCP_STANDALONENo1 makes a stdio start run inline even when the daemon is healthy
ENGRAM_RERANK_ENABLEDNoSet to false or 0 to disable the cross-encoder rerankertrue
ENGRAM_SKIP_PREFLIGHTNoSet to 1 to silence the npm install platform preflight
ENGRAM_MODEL_CACHE_DIRNoWhere model weights are downloaded/cached; never inside node_modules
ENGRAM_NO_UPDATE_CHECKNoSet to 1 to disable the automatic daily version lookup and notice
ENGRAM_OPENAI_BASE_URLNoGeneric OpenAI-compatible route: OpenAI, a LiteLLM gateway, a self-hosted server. A bare origin gets `/v1` appendedhttps://api.openai.com/v1
ENGRAM_OPENROUTER_MODELNoOpenRouter model namegoogle/gemini-2.5-flash-lite
ENGRAM_CHUNKING_STRATEGYNofixed or adaptive (content-aware boundaries)fixed
ENGRAM_WORKER_TIMEOUT_MSNoPer-call timeout; remember, remember_batch, index_file_structure and reflect --refresh use higher floors.8000
ENGRAM_OPENAI_API_KEY_ENVNoName of the environment variable holding the route's credential. Engram reads it at call time and never stores, prints or commits the valueOPENAI_API_KEY
ENGRAM_OPENAI_TEMPERATURENoSent only when set; the generic route omits `temperature` by default because many gateways and reasoning models reject it
ENGRAM_CLAUDE_PROJECTS_DIRNoWhere engram sync looks for Claude Code conversations
ENGRAM_FORGET_RETENTION_DAYSNoDays a forgotten memory is kept before hard-delete30
ENGRAM_LOCAL_MODEL_FALLBACKSNoComma-separated Ollama models tried in order when ENGRAM_LOCAL_MODEL is not pulled

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

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