Vigil
by leo-bone
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VIGIL_CONFIG | No | Path to the vigil.config.json governance config file (overrides the default path). The config file can only tighten built-in default policy. | |
| VIGIL_LEDGER | No | Path to the ledger file/backend. A path ending in .db / .sqlite uses the SQLite backend (for concurrent multi-process writes); otherwise the NDJSON backend (single process) is used. | |
| VIGIL_SHADOW | No | Enable shadow mode (e.g. VIGIL_SHADOW=1). In shadow mode Vigil only records to the ledger without intercepting, useful for validating false-positive rate before enabling enforcement. | |
| TYPESAFE_API_KEY | No | API key for the TypeSafe Jev cloud judgment model backend. One of three judgment backends (local via VIGIL_LOCAL_JUDGE, TypeSafe cloud, or MockJudge when neither is set). | |
| VIGIL_LOCAL_JUDGE | No | Points to a local decision service (strands-decider / laya, /v1/systemone dialect) used as the judgment model backend. Zero cost, data stays local, can be fine-tuned with your own data. | |
| VIGIL_SHOW_SQLITE_WARNING | No | Set to 1 to surface the experimental node:sqlite warning that is otherwise suppressed. |
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
| 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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues