Cortex
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORIA_HOST | No | HTTP bind | 127.0.0.1 |
| MEMORIA_PORT | No | HTTP bind | 7437 |
| MEMORIA_DB_PATH | No | Explicit DB file (wins over DATA_DIR; :memory: supported) | |
| MEMORIA_PROJECT | No | Override project detection | auto-detected from cwd |
| MEMORIA_DATA_DIR | No | Directory holding memoria.db | ~/.memoria |
| MEMORIA_AUTH_TOKEN | No | If set, HTTP requires Authorization: Bearer <token> (except /api/health) | |
| MEMORIA_WORKSPACE_ID | No | Workspace used by CLI/stdio | 1 |
| MEMORIA_REDACT_ON_READ | No | 1 also redacts on the way out, not just on write | off |
| MEMORIA_EMBEDDING_MODEL | No | Any 384-dim feature-extraction model | Xenova/all-MiniLM-L6-v2 |
| MEMORIA_SEMANTIC_SEARCH | No | 1 enables embeddings + hybrid search | off |
| MEMORIA_EMBEDDING_CACHE_DIR | No | Where model files are cached | transformers default |
| MEMORIA_UNLIMITED_WORKSPACES | No | CSV of workspace ids exempt from quotas — set it to 1 for personal self-hosting |
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
ActivityMaintained
ResponsivenessNo issues