@mnemon-dev/dsh-mnemon

Configuration

Environment Variable	Default	Description
MNEMON_DATA_DIR	~/.mnemon	Base data directory
MNEMON_STORE	(active file or default)	Named memory store for data isolation

Retention:

Environment Variable	Default	Description
MNEMON_MAX_INSIGHTS	1000	Active-insight ceiling; 0 disables automatic pruning
MNEMON_AUTO_PRUNE_MIN_AGE	24h	Grace period before an insight can be auto-pruned; accepts 24h, 7d, or 0

Each automatic deletion is soft, appears in the oplog as a prune operation, and is reported by ID in the triggering command's auto_pruned_ids field.

Embedding (only relevant if using embeddings):

Environment Variable	Default	Description
MNEMON_EMBED_ENDPOINT	http://localhost:11434	Embedding API endpoint
MNEMON_EMBED_MODEL	nomic-embed-text	Embedding model name
MNEMON_EMBED_PROTOCOL	(auto-detect)	ollama or openai; auto-detected from an endpoint ending in /v1
MNEMON_EMBED_API_KEY	(none)	Bearer token for OpenAI-compatible servers (oMLX, vLLM, etc.)
MNEMON_EMBED_DIMENSIONS	(native)	Optional Matryoshka dimension truncation

The embedding client speaks the Ollama API by default and the OpenAI-compatible embeddings API when the endpoint ends in /v1 (or when MNEMON_EMBED_PROTOCOL=openai is set). OpenAI-compatible servers are normally probed via their models route; servers that do not serve that route (e.g. Voyage AI) are detected via an embeddings round-trip instead. For example, a local server such as oMLX can be configured with:

export MNEMON_EMBED_ENDPOINT=http://127.0.0.1:18000/v1
export MNEMON_EMBED_MODEL=bge-m3-mlx-8bit
export MNEMON_EMBED_API_KEY=sk-... # omit for keyless local servers
mnemon embed --status

A hosted provider such as Voyage AI needs only the endpoint, model, and key:

export MNEMON_EMBED_ENDPOINT=https://api.voyageai.com/v1
export MNEMON_EMBED_MODEL=voyage-3.5
export MNEMON_EMBED_API_KEY=pa-...
mnemon embed --status