Open Mind
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENMIND_DATA_DIR | No | Where the learned index lives (SQLite + Chroma + map files). | ./data |
| OPENMIND_MACHINE_DIR | No | Machine-local sidecar holding each project's absolute source root (kept *outside* data/ so the index stays portable). | ~/.openmind |
| OPENMIND_EMBED_DEVICE | No | cpu · smart (GPU when the card is free, else CPU) · auto (always GPU if available) · gpu. | smart |
| OPENMIND_EMBED_OFFLINE | No | 1 forces the deterministic hashing embedder (no model download). | 0 |
| OPENMIND_ENRICH_EGRESS | No | 0 disables the audited Wikipedia enrichment lookup (fully offline). | 1 |
| OPENMIND_INGEST_FREE_GPU | No | Briefly stop a managed model server during the embed pass to free VRAM for GPU embedding, then restart it. | 1 |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/HelloThisWorld/open-mind'
If you have feedback or need assistance with the MCP directory API, please join our Discord server