scholar-memory
by byBasiliosP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub token for code search (optional, prevents 401 rate limits). | |
| OPENAI_API_KEY | No | OpenAI API key for embeddings (required for cloud backend, unless using LM Studio). | |
| ANTHROPIC_API_KEY | No | Anthropic API key for strong model in normal/deep research depth. | |
| SCHOLAR_MEMORY_DB | No | Path to SQLite database file. | ~/.scholaragent/memory.db |
| SCHOLAR_MEMORY_DIR | No | Data directory for memory store. | ~/.scholaragent |
| SCHOLAR_CHEAP_MODEL | No | Cheap model name for Scout agent. | gpt-4o-mini |
| SCHOLAR_LMSTUDIO_URL | No | LM Studio endpoint when using lmstudio backend. | http://localhost:1234/v1 |
| SCHOLAR_STRONG_MODEL | No | Strong model name for analysis agents. | claude-sonnet-4-6 |
| SCHOLAR_CHEAP_BACKEND | No | Backend for Scout agent (e.g., openai, lmstudio). | openai |
| SCHOLAR_STRONG_BACKEND | No | Backend for analysis agents (e.g., anthropic, openai, lmstudio). | anthropic |
| SCHOLAR_EMBEDDING_MODEL | No | Embedding model name. | text-embedding-3-small |
| SCHOLAR_EMBEDDING_BACKEND | No | Embedding backend: 'openai' or 'lmstudio'. | openai |
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
ActivityInactive
ResponsivenessNo issues