Schema | Engram

Engram

Describes the environment variables required to run the server.

Name	Required	Description
`USER_TZ`	Yes	Your timezone, e.g. Asia/Kolkata
`DATA_DIR`	No	Directory containing your documents (keep out of git)
`USER_NAME`	Yes	How prompts refer to you
`ADMIN_TOKEN`	No	Bearer token required for remote or tunnelled requests
`GROQ_API_KEY`	No	API key for Groq
`GEMINI_API_KEY`	No	API key for Gemini
`OPENAI_API_KEY`	No	API key for OpenAI
`MISTRAL_API_KEY`	No	API key for Mistral
`MEMORY_LLM_CHAIN`	No	Comma-separated list of LLM providers to try in order, e.g. together,ollama
`TOGETHER_API_KEY`	No	API key for Together AI (alternative: use GEMINI_API_KEY, GROQ_API_KEY, MISTRAL_API_KEY, OPENAI_API_KEY, ANTHROPIC_API_KEY, or local Ollama)
`ANTHROPIC_API_KEY`	No	API key for Anthropic
`CONNECTION_STRING`	Yes	PostgreSQL connection string, e.g. postgresql+asyncpg://postgres:postgres@localhost:5432/engram
`ENGRAM_BACKUP_DIR`	No	Directory for encrypted backups (can point to a private git repo)
`TEST_DATABASE_URL`	No	Test database URL for development (defaults to <CONNECTION_STRING db>_test)
`MEMORY_MODEL_TOGETHER`	No	Model name for Together provider, e.g. deepseek-ai/DeepSeek-V4-Flash-0731

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityMaintained

ResponsivenessNo issues