Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OUTSOURCE_MODELNoThe model to use, e.g. "qwen3:4b" for a local Ollama model.
OUTSOURCE_ROOTSNoDirectories that file inclusion is sandboxed to. File inclusion is off until you name the roots.
OUTSOURCE_CONFIGNoPath to a config file that is granted full authority (including keys a project-level .outsource.toml may not set).
OUTSOURCE_MODELSNoModel alias configuration (maps aliases to fallback chains, possibly mixing providers).
OUTSOURCE_TIMEOUTNoRequest timeout.
OPENROUTER_API_KEYNoYour OpenRouter API key (e.g. sk-or-v1-...), obtained from openrouter.ai/keys. Required unless you use a free local model instead.
OUTSOURCE_BASE_URLNoCustom base URL for the provider API.
OUTSOURCE_PROVIDERNoThe provider to use, e.g. "openrouter" or "ollama".
OUTSOURCE_LOG_LEVELNoLogging level.
OUTSOURCE_STATE_DIRNoDirectory where state (e.g. the spend ledger) is stored.
OUTSOURCE_BUDGET_USDNoMonthly spending cap in USD.
OUTSOURCE_MAX_TOKENSNoMaximum number of tokens for a response.
OUTSOURCE_CONCURRENCYNoMaximum concurrency for batch tasks.
OUTSOURCE_OLLAMA_BASE_URLNoBase URL of the local Ollama server.
OUTSOURCE_DAILY_BUDGET_USDNoDaily spending cap in USD.
OUTSOURCE_MAX_COST_PER_CALL_USDNoPer-call cost ceiling in USD. Defaults to $0.25 when unset.

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

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