Vektor Memory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VEKTOR_DEBUG | No | Enable verbose retrieval debug output. | |
| VEKTOR_MODEL | No | Swap embedding model. | Xenova/bge-small-en-v1.5 |
| VEKTOR_RERANK | No | Enable cross-encoder reranking. | true |
| VEKTOR_TRIPLES | No | Enable batch triple extraction on ingest. | true |
| VEKTOR_TEMPORAL | No | Enable temporal index and date boosting. | true |
| VEKTOR_FORESIGHT | No | Extract future-tense foresight signals. | true |
| VEKTOR_SUMMARIZE | No | Enable LLM session summarisation on ingest. | false |
| VEKTOR_CONTRADICT | No | Enable ADD-only contradiction detection. | true |
| CLOAK_PROJECT_PATH | No | Path to your project for cloak operations. | |
| VEKTOR_LICENCE_KEY | Yes | Your licence key for VEKTOR memory. |
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 | |
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/Vektor-Memory/Vektor-memory'
If you have feedback or need assistance with the MCP directory API, please join our Discord server