Schema | io.github.labacacia/banyan-memory

io.github.labacacia/banyan-memory

Official

Describes the environment variables required to run the server.

Name	Required	Description	Default
`BANYAN_EMBEDDER`	No	The embedder to use. Set to 'onnx' to use ONNX embeddings; otherwise uses hashing fallback.
`IVY_ACT_NODE_ENABLED`	No	Set to 'true' to enable Ivy Act Node SDK runtime.
`IVY_ACT_NODE_HUB_URL`	No	URL of the Ivy Hub.
`IVY_ACT_NODE_TENANT_ID`	No	Tenant ID for Ivy Hub. Default: _local.	_local
`BANYAN_NIP_CA_PASSPHRASE`	No	Passphrase for initializing the embedded NID CA. Used in full governed setup.
`IVY_ACT_NODE_ACCESS_TOKEN`	No	Access token for Ivy Hub.
`IVY_ACT_NODE_WORKSPACE_ID`	No	Workspace ID for Ivy Hub. Default: default.	default
`BANYAN_DISCLOSURE_QUALITY_MODE`	No	Mode for disclosure quality: 'advisory' or 'required'.
`BANYAN_GOVERNANCE_BACKFILL_DRY_RUN`	No	Preview the legacy backfill run without applying changes.
`BANYAN_GOVERNANCE_BACKFILL_RESTART`	No	Set to 'true' to force a full rescan.
`BANYAN_DISCLOSURE_QUALITY_TIMEOUT_MS`	No	Timeout for disclosure quality evaluation in milliseconds. Default: 2000.	2000
`BANYAN_GOVERNANCE_BACKFILL_BATCH_SIZE`	No	Batch size for legacy backfill.
`BANYAN_DISCLOSURE_GROUNDING_MIN_COVERAGE`	No	Minimum coverage for grounding. Default: 0.8.	0.8
`BANYAN_GOVERNANCE_BACKFILL_ITEMS_PER_SECOND`	No	Rate limit for backfill items per second.
`BANYAN_GOVERNANCE_BACKFILL_MAX_ITEMS_PER_RUN`	No	Maximum items to backfill per run.

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