Skip to main content
Glama
labacacia

io.github.labacacia/banyan-memory

Official
by labacacia

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BANYAN_EMBEDDERNoThe embedder to use. Set to 'onnx' to use ONNX embeddings; otherwise uses hashing fallback.
IVY_ACT_NODE_ENABLEDNoSet to 'true' to enable Ivy Act Node SDK runtime.
IVY_ACT_NODE_HUB_URLNoURL of the Ivy Hub.
IVY_ACT_NODE_TENANT_IDNoTenant ID for Ivy Hub. Default: _local._local
BANYAN_NIP_CA_PASSPHRASENoPassphrase for initializing the embedded NID CA. Used in full governed setup.
IVY_ACT_NODE_ACCESS_TOKENNoAccess token for Ivy Hub.
IVY_ACT_NODE_WORKSPACE_IDNoWorkspace ID for Ivy Hub. Default: default.default
BANYAN_DISCLOSURE_QUALITY_MODENoMode for disclosure quality: 'advisory' or 'required'.
BANYAN_GOVERNANCE_BACKFILL_DRY_RUNNoPreview the legacy backfill run without applying changes.
BANYAN_GOVERNANCE_BACKFILL_RESTARTNoSet to 'true' to force a full rescan.
BANYAN_DISCLOSURE_QUALITY_TIMEOUT_MSNoTimeout for disclosure quality evaluation in milliseconds. Default: 2000.2000
BANYAN_GOVERNANCE_BACKFILL_BATCH_SIZENoBatch size for legacy backfill.
BANYAN_DISCLOSURE_GROUNDING_MIN_COVERAGENoMinimum coverage for grounding. Default: 0.8.0.8
BANYAN_GOVERNANCE_BACKFILL_ITEMS_PER_SECONDNoRate limit for backfill items per second.
BANYAN_GOVERNANCE_BACKFILL_MAX_ITEMS_PER_RUNNoMaximum items to backfill per run.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/labacacia/banyan-brain-lite'

If you have feedback or need assistance with the MCP directory API, please join our Discord server