wolfmem
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WOLFMEM_HOME | No | Data directory for wolfmem. Defaults to ~/.wolfmem. | ~/.wolfmem |
| WOLFMEM_EMB_KEY | No | API key for the OpenAI-compatible embedding endpoint (e.g. siliconflow bge-m3). If not configured, wolfmem uses zero-network keyword recall. | |
| WOLFMEM_LLM_KEY | No | API key for the distiller LLM endpoint. | |
| WOLFMEM_LLM_MODEL | No | Model name to use for the distiller LLM. Any OpenAI-compatible model works. | |
| WOLFMEM_MAX_FACTS | No | Maximum number of facts to store before evicting the least important or least recalled facts. Defaults to 800. | 800 |
| WOLFMEM_LLM_API_BASE | No | OpenAI-compatible base URL for the distiller LLM endpoint. Do not include the /chat/completions suffix. |
Instructions
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.
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues