Skip to main content
Glama
Adityaladi

OpenCode Brain

by Adityaladi

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GRAPH_PATHNoKnowledge graph persistence path~/.opencode-brain/graph.json
QDRANT_HOSTNoQdrant server hostlocalhost
QDRANT_PORTNoQdrant server port6333
FAST_MODEL_IDNoFast default LLM for note construction and extractionQwen/Qwen3-4B-Instruct-2507
HARD_MODEL_IDNoHard fallback model for synthesis and memory evolutionQwen/Qwen3-30B-A3B-Instruct-2507
OBSIDIAN_HOSTNoObsidian REST API URLhttp://localhost:27123
EMBEDDING_MODELNoEmbedding modelsentence-transformers/all-MiniLM-L6-v2
OBSIDIAN_API_KEYNoObsidian Local REST API key (empty disables sync)
QDRANT_COLLECTIONNoCollection nameopencode_brain
FAST_MODEL_PROVIDERNoInference provider for the fast model (overridden to nscale in .env)featherless-ai
HARD_MODEL_PROVIDERNoInference provider for the hard modelfeatherless-ai
HUGGINGFACE_API_KEYYesRequired
STALE_DAYS_THRESHOLDNoDays before a note is stale45
STALE_ACCESS_THRESHOLDNoMin accesses to be immune from archival2
OBSIDIAN_VAULT_SUBFOLDERNoSubfolder in vault for notesbrain

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

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/Adityaladi/AI-Bain'

If you have feedback or need assistance with the MCP directory API, please join our Discord server