Struct MemoryConfig 

pub struct MemoryConfig {

    pub enabled: bool,
    pub db_path: String,
    pub embedding_provider: String,
    pub embedding_model: String,
    pub openai_api_key: Option<String>,
    pub cohere_api_key: Option<String>,
    pub auto_capture: bool,
    pub vector_weight: f32,
    pub bm25_weight: f32,
    pub inject_context: bool,
    pub max_context_tokens: u32,
    pub mcp_http_enabled: bool,
    pub mcp_http_path: String,
    pub namespace: String,
    pub database: String,
    pub surreal_endpoint: Option<String>,
    pub surreal_user: Option<String>,
    pub surreal_pass: Option<String>,
}

Configuration for the in-process agent memory system, backed by surreal-memory + SurrealDB/SurrealKV.

Fields

enabled: bool

Enable the memory system (default: false — opt-in).

db_path: String

Path to the SurrealKV data directory for embedded mode.

embedding_provider: String

Embedding provider: “openai” | “cohere” | “local”

embedding_model: String

Embedding model identifier (provider-specific).

openai_api_key: Option<String>

OpenAI API key for embeddings (used when embedding_provider = “openai”).

cohere_api_key: Option<String>

Cohere API key for embeddings (used when embedding_provider = “cohere”).

auto_capture: bool

Auto-capture memories from conversations after each assistant turn.

vector_weight: f32

weight applied to the vector-similarity score in hybrid search (0.0–1.0).

bm25_weight: f32

Weight applied to the BM25 full-text score in hybrid search (0.0–1.0).

inject_context: bool

Inject relevant memory context into LLM prompts before each call.

max_context_tokens: u32

Maximum tokens to include in an injected memory context block.

mcp_http_enabled: bool

Expose the memory MCP tools over HTTP at mcp_http_path.

mcp_http_path: String

URL path for the streamable-HTTP MCP memory endpoint.

namespace: String

SurrealDB namespace for memory storage.

database: String

SurrealDB database name for memory storage.

surreal_endpoint: Option<String>

External SurrealDB endpoint (ws:// or wss://). When set, overrides embedded mode. Env var: UAR_MEMORY__SURREAL_ENDPOINT

surreal_user: Option<String>

Username for the external SurrealDB instance. Env var: UAR_MEMORY__SURREAL_USER

surreal_pass: Option<String>

Password for the external SurrealDB instance. Env var: UAR_MEMORY__SURREAL_PASS

Trait Implementations

impl Clone for MemoryConfig

fn clone(&self) -> MemoryConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for MemoryConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for MemoryConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for MemoryConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for MemoryConfig

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.