Syllabuddy
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HF_TOKEN | No | Hugging Face write token, used by deploy/publish_space.py to create the Docker Space and store the model API key as a Space secret. | |
| AWS_REGION | No | AWS region for the Amazon Bedrock brain, required when SYLLABUDDY_BRAIN=bedrock. | |
| SPACE_HOST | No | On Hugging Face Spaces, set automatically in place of SYLLABUDDY_PUBLIC_URL to enable the OAuth 2.1 authorization server. | |
| BEDROCK_MODEL_ID | No | Amazon Bedrock model ID, used when SYLLABUDDY_BRAIN=bedrock. | us.amazon.nova-pro-v1:0 |
| SYLLABUDDY_BRAIN | No | Selects the agent "brain". Use "openai" for Groq or any OpenAI-compatible API (also used for Ollama, fully local), or "bedrock" for Amazon Bedrock. With no configuration the app runs in offline mode: no model and no keys, just a simple intent router, but still fully working through MCP. | offline |
| AWS_ACCESS_KEY_ID | No | AWS credentials, required when SYLLABUDDY_BRAIN=bedrock (Amazon Bedrock brain, optional; implemented and tested with a stubbed client, not yet run against a live account). | |
| SYLLABUDDY_LLM_MODEL | No | Model name to use with the OpenAI-compatible LLM API. | |
| AWS_SECRET_ACCESS_KEY | No | AWS credentials, required when SYLLABUDDY_BRAIN=bedrock (Amazon Bedrock brain, optional; implemented and tested with a stubbed client, not yet run against a live account). | |
| SYLLABUDDY_PUBLIC_URL | No | When set, Syllabuddy is also an OAuth 2.1 authorization server. A client such as Alexa+ account linking or Claude discovers it from the 401 on /mcp, registers itself, and sends the student to /link to sign in. | |
| SYLLABUDDY_LLM_API_KEY | No | API key for the OpenAI-compatible LLM API (e.g. Groq, used for the demo). | |
| SYLLABUDDY_LLM_BASE_URL | No | Base URL of the OpenAI-compatible LLM API. For Ollama (fully local) set SYLLABUDDY_BRAIN=openai and SYLLABUDDY_LLM_BASE_URL=http://localhost:11434/v1 with a tool-calling model. |
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