engram
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ENGRAM_DB_PATH | No | SQLite database file path (default: ~/.engram/memory.sqlite) | |
| OPENAI_API_KEY | Yes | OpenAI API key (required for OpenAI or Anthropic provider; for Ollama, set ENGRAM_PROVIDER=ollama and omit API keys) | |
| ENGRAM_PROVIDER | No | AI provider: openai, anthropic, ollama (default: openai) | |
| ANTHROPIC_API_KEY | No | Anthropic API key (required if using Anthropic provider) | |
| ENGRAM_AUTO_REFLECT | No | Set to false to disable auto-reflect (default: true) | |
| ENGRAM_DEFAULT_BANK | No | Default bank ID (default: default) | |
| ENGRAM_LANGUAGE_MODEL | No | Override language model name (default: provider default) | |
| ENGRAM_EMBEDDING_MODEL | No | Override embedding model name (default: provider default) | |
| ENGRAM_DEFAULT_BANK_NAME | No | Default bank name (default: Default) | |
| ENGRAM_SKIP_EVIDENCE_EVAL | No | Set to true to skip evidence evaluation (default: false) | |
| ENGRAM_REFLECT_MAX_CLUSTERS | No | Max clusters per reflect cycle (default: unlimited) |
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
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessUnresponsive