Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PI_RUN_ROOTNoState directory.~/.cache/pi-runs
PI_ROUTER_DBNoOptional SQLite path; token totals are read with `sqlite3 -readonly`. Missing DB yields null tokens.
PI_MODELS_URLNoModels endpoint URL. No credentials are read or sent.http://127.0.0.1:20128/v1/models
PI_POLICY_PATHNoOptional path to a policy JSON checked before launch.
PI_FALLBACK_ROWNoComma-separated ordered fallback model IDs.
PI_STATUS_SCRIPTNoAbsolute path to the executable taking a log path and printing status; default `pi-status.sh` looked up on PATH. Set this unless the script is on PATH.pi-status.sh
PI_DURABLE_SCRIPTNoAbsolute path to the executable taking `worktree session model brief_path`; default `durable-pi.sh` looked up on PATH. Set this unless the script is on PATH.durable-pi.sh
PI_HEADROOM_SCRIPTNoExecutable accepting `--json`, returning an array or `{pools: [...]}` of `pool`, `status`, `percent_left`, `resets`.

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

Maintenance

ActivityMaintained
ResponsivenessNo issues