codewatch-memory
by KlausAndrade
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_API_KEY | No | Groq API key | |
| OPENAI_API_KEY | No | OpenAI API key | |
| CODEWATCH_DATA_DIR | No | SQLite storage location | ~/mcp-data/codewatch-memory/ |
| CODEWATCH_LOG_LEVEL | No | Logging verbosity | info |
| CODEWATCH_GROQ_MODEL | No | Groq model to use | llama-3.3-70b-versatile |
| CODEWATCH_AUTO_REFLECT | No | Enable auto-reflection | true |
| CODEWATCH_GOOGLE_MODEL | No | Google model to use | gemini-2.5-flash |
| CODEWATCH_LLM_PROVIDER | No | Primary LLM provider (google, openai, groq) | |
| CODEWATCH_OPENAI_MODEL | No | OpenAI model to use | gpt-4o-mini |
| CODEWATCH_MAX_COMPRESSION | No | Max compression level (0-3) | 3 |
| CODEWATCH_FALLBACK_PROVIDER | No | Fallback LLM provider (google, openai, groq, none) | openai |
| CODEWATCH_REFLECT_THRESHOLD | No | Auto-reflect trigger threshold in tokens | 40000 |
| GOOGLE_GENERATIVE_AI_API_KEY | No | Google API key |
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