Hippocampus
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port on which the MCP server (POST /mcp) and brain view (GET /) are served. | 3000 |
| DEMO_EPOCH | No | Set DEMO_EPOCH=<ms> for a reproducible demo: the clock is frozen except for /api/timeskip, and ids are deterministic. | |
| MEMORY_DIR | No | Storage folder for the memory store. | data/memory |
| MEMORY_LLM | No | Set to `openai` to use LLM summaries and reconstruction instead of the default extractive summarizer. | |
| OPENAI_MODEL | No | Optional model name when MEMORY_LLM=openai. | |
| OPENAI_API_KEY | No | API key used when MEMORY_LLM=openai for LLM summaries and reconstruction. | |
| OPENAI_BASE_URL | No | Optional base URL for an OpenAI-compatible endpoint when MEMORY_LLM=openai. | |
| MEMORY_BUDGET_BYTES | No | Storage budget in bytes. When exceeded, the weakest memories are forced down to cool, then cold (fidelity floors still apply). If the store is still over budget, the server raises an alert instead of deleting. | unlimited |
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 issues