Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_API_KEY | No | Groq API key for cloud enrichment backend | |
| BRAINLAYER_DB | No | Database file path | ~/.local/share/brainlayer/brainlayer.db |
| BRAINLAYER_MLX_URL | No | MLX server endpoint | http://127.0.0.1:8080/v1/chat/completions |
| BRAINLAYER_GROQ_URL | No | Groq API endpoint | https://api.groq.com/openai/v1/chat/completions |
| BRAINLAYER_MLX_MODEL | No | MLX model identifier | mlx-community/Qwen2.5-Coder-14B-Instruct-4bit |
| BRAINLAYER_GROQ_MODEL | No | Groq model for enrichment | llama-3.3-70b-versatile |
| BRAINLAYER_OLLAMA_URL | No | Ollama API endpoint | http://127.0.0.1:11434/api/generate |
| BRAINLAYER_ENRICH_MODEL | No | Ollama model name | glm-4.7-flash |
| BRAINLAYER_STALL_TIMEOUT | No | Seconds before killing a stuck enrichment chunk | 300 |
| BRAINLAYER_ENRICH_BACKEND | No | Enrichment LLM backend (mlx, ollama, or groq). Defaults to auto-detection (MLX → Ollama → Groq). | |
| BRAINLAYER_HEARTBEAT_INTERVAL | No | Log progress every N chunks during enrichment | 25 |
| BRAINLAYER_SANITIZE_USE_SPACY | No | Use spaCy NER for PII detection | true |
| BRAINLAYER_SANITIZE_EXTRA_NAMES | No | Comma-separated names to redact from indexed content |
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 | |