Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_PROXY | No | Corporate HTTP proxy URL (if needed) | |
| HTTPS_PROXY | No | Corporate HTTPS proxy URL (if needed) | |
| MIMIR_LLM_API | No | Base URL for the LLM API endpoint | http://copilot-api:4141 |
| SSL_CERT_FILE | No | Custom CA certificate file path (if needed) | |
| MIMIR_PM_MODEL | No | Optional per-agent model override for PM agent (defaults to MIMIR_DEFAULT_MODEL) | |
| MIMIR_QC_MODEL | No | Optional per-agent model override for QC agent (defaults to MIMIR_DEFAULT_MODEL) | |
| NEO4J_PASSWORD | No | Neo4j database password (change in production!) | password |
| MIMIR_LLM_API_KEY | No | Optional API key for LLM provider (required for OpenAI API) | dummy-key |
| MIMIR_LLM_API_PATH | No | Optional path for LLM API chat completions endpoint | /v1/chat/completions |
| MIMIR_WORKER_MODEL | No | Optional per-agent model override for Worker agent (defaults to MIMIR_DEFAULT_MODEL) | |
| HOST_WORKSPACE_ROOT | No | Your main source code directory. This gives Mimir access to your code for file indexing. Tilde (~) automatically expands to your home directory. | ~/src |
| MIMIR_DEFAULT_MODEL | No | Default LLM model to use | gpt-4.1 |
| MIMIR_EMBEDDINGS_API | No | Embeddings API endpoint | http://llama-server:8080 |
| MIMIR_AUTO_INDEX_DOCS | No | Auto-index Mimir documentation on startup. Allows users to immediately query Mimir's docs via semantic search. | true |
| MIMIR_DEFAULT_PROVIDER | No | LLM provider selection. Options: openai, copilot, ollama, llama.cpp | openai |
| MIMIR_EMBEDDINGS_MODEL | No | Embedding model for semantic search. Options: bge-m3, nomic-embed-text, text-embedding-3-small | bge-m3 |
| MIMIR_EMBEDDINGS_ENABLED | No | Enable vector embeddings for AI semantic search | true |
| MIMIR_EMBEDDINGS_API_PATH | No | Optional path for embeddings API endpoint | /v1/embeddings |
| MIMIR_LLM_API_MODELS_PATH | No | Optional path for LLM API models endpoint | /v1/models |
| MIMIR_EMBEDDINGS_CHUNK_SIZE | No | Chunk size for embeddings | 768 |
| MIMIR_EMBEDDINGS_DIMENSIONS | No | Embedding vector dimensions | 1024 |
| MIMIR_FEATURE_VECTOR_EMBEDDINGS | No | Enable vector embeddings feature flag | true |
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 | |