l0-memory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LTM_DB | No | Override path to the SQLite database. | ~/.long-term-memory/memories.db |
| LTM_DEBUG | No | Set to '1' to enable timestamped diagnostic lines on stderr. | |
| LTM_LOG_FILE | No | Path to a file to append diagnostic lines to. Implies LTM_DEBUG. | |
| LTM_EMBEDDING_URL | No | OpenAI-compatible /v1/embeddings base URL. Empty means FTS-only search. | |
| LTM_EMBED_DISABLE | No | Set to '1' to force the vector path off even when an embedding URL is set. | |
| LTM_EMBED_TIMEOUT | No | Per-request timeout for embedding calls (Go duration). | 5s |
| LTM_EMBEDDING_MODEL | No | Embedding model name passed to the endpoint. | |
| LTM_CONFLICT_DISABLE | No | Set to '1' to disable automatic local conflict resolution (auto-supersede) on save. |
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
ResponsivenessUnresponsive