ankra ai

Configure the organisation’s AI provider, credentials, custom OpenAI-compatible endpoints, and the model catalog the chat picker offers. Mutations require the ai.manage permission (organisation admins by default); the provider status and the model listing are available to every member.

ankra ai anthropic

Manage the custom Anthropic API key

ankra ai anthropic delete

Remove the custom Anthropic API key

ankra ai anthropic delete [flags]

Flags

Flag	Default	Description
`--yes`	`false`	Skip the confirmation prompt

ankra ai anthropic set

Store and validate a custom Anthropic API key (must start with sk-ant-).

ankra ai anthropic set [flags]

Flags

Flag	Default	Description
`--api-key`		Anthropic API key (starts with sk-ant-)
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai autonomy

Read and operate the organisation-wide AI kill switch. Engaging it stops all AI for everyone in the organisation: running sessions and agent runs are cancelled, and chat is refused until it is released. Reach for it during an incident, not to tighten a policy - a narrower stop lives in the auto-remediation policy, which ‘ankra ai remediation policy’ reads.

ankra ai autonomy pause

Pause autonomous actions across the organisation. Chat, diagnosis and read-only investigation keep working; what stops is the AI changing anything without a person approving it first. It switches off auto-remediation and pauses every enabled agent, and records exactly what it switched off - so resuming restores that and nothing else, from any terminal or browser, by any administrator. To stop AI entirely during an incident, use “ankra ai autonomy stop-all”.

ankra ai autonomy pause [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)
`--reason`		Why autonomous actions are paused

ankra ai autonomy resume

Resume autonomous actions. Only what the pause switched off is restored: an agent somebody disabled deliberately stays disabled.

ankra ai autonomy resume [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai autonomy start-all

Let AI run again for the organisation

ankra ai autonomy start-all [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai autonomy status

Show whether AI is stopped for the organisation

ankra ai autonomy status [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai autonomy stop-all

Stop all AI for everyone in the organisation. Every running AI session and agent run is cancelled, pending approvals expire, and chat is refused until the switch is released. The reason is shown to administrators alongside the switch.

ankra ai autonomy stop-all [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)
`--reason`		Why AI is being stopped (shown to administrators)
`--yes`	`false`	Skip the confirmation prompt

ankra ai board-identity

Manage the organisation’s board agent identity. Agents the platform created - the preloaded team - have no user account of their own, so their headless runs cannot change anything. The board identity gives them one, with its own role, so their work is attributable to the agent rather than to whoever set it up. It cannot sign in and has no token. Without it, a designated board worker is escalated to a human on every ticket instead of working it.

ankra ai board-identity provision

Give the board an identity its agents act as

ankra ai board-identity provision [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)
`--role`		Role the identity carries: operator (default), member, or viewer

ankra ai board-identity revoke

Stand the board identity down. The principal itself is kept so its past actions stay attributable; what it loses is every grant above the viewer floor, which makes the board’s agents ineligible again on the next dispatcher pass.

ankra ai board-identity revoke [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)
`--yes`	`false`	Skip the confirmation prompt

ankra ai board-identity status

Show whether the board has an identity

ankra ai board-identity status [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai endpoints

Manage custom OpenAI-compatible endpoints

ankra ai endpoints create

Add a named OpenAI-API-standard endpoint (OpenRouter, vLLM, LiteLLM, Ollama, …). The server validates and probes the endpoint before saving; the API key is stored server-side and never returned.

ankra ai endpoints create [flags]

Flags

Flag	Default	Description
`--api-key`		API key for the endpoint
`--base-url`		OpenAI-compatible base URL (e.g. https://openrouter.ai/api/v1)
`--name`		Endpoint name
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai endpoints delete

Delete an endpoint and its stored key. Catalog models on it are removed too.

ankra ai endpoints delete <endpoint_id> [flags]

Flags

Flag	Default	Description
`--yes`	`false`	Skip the confirmation prompt

ankra ai endpoints discover

Query the endpoint’s /models list so you know which model ids to reference.

ankra ai endpoints discover <endpoint_id> [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai endpoints list

List configured OpenAI-compatible endpoints

ankra ai endpoints list [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai endpoints update

Update an endpoint’s name, base URL, and optionally rotate its key. Omit --api-key to keep the stored key.

ankra ai endpoints update <endpoint_id> [flags]

Flags

Flag	Default	Description
`--api-key`		New API key (omit to keep the stored key)
`--base-url`		OpenAI-compatible base URL
`--name`		Endpoint name
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai lanes

Choose the model each AI function runs on. A lane is one AI function that runs outside chat: deploy analysis, troubleshooting, CI/CD generation, stack README generation and AI code review. A lane with no selection follows its default tier in the model catalog (‘ankra ai models list’), so it moves when the catalog does.

ankra ai lanes clear

Return a lane to its default tier

ankra ai lanes clear <lane> [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai lanes list

List each AI lane with the model it runs on

ankra ai lanes list [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai lanes set

Run a lane on a catalog model or an exact OpenRouter model. <model> is a catalog key from ‘ankra ai models list’ (for example think or expert) or an exact OpenRouter model id (for example z-ai/glm-5.2). Changing a lane requires organisation admin.

ankra ai lanes set <lane> <model> [flags]

Examples

ankra ai lanes set pr_review think
  ankra ai lanes set stack_description z-ai/glm-5.2

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai models

Manage the organisation model catalog

ankra ai models create

Add a model to the catalog. For an Ankra-managed Claude model pass --model-id (e.g. claude-opus-5). For a model served by a custom OpenAI-compatible endpoint, also pass --endpoint with the endpoint id (see ‘ankra ai endpoints list’).

ankra ai models create [flags]

Flags

Flag	Default	Description
`--context-window`	`200000`	Context window in tokens
`--description`		Short description
`--enabled`	`true`	Model is selectable in the picker
`--endpoint`		OpenAI-compatible endpoint id (omit for Ankra-managed Claude)
`--key`		Catalog key (lowercase slug; the model_mode value)
`--max-output`	`8192`	Maximum output tokens
`--model-id`		Provider model id (e.g. claude-opus-5 or gpt-4o)
`--name`		Display name shown in the picker
`-o`, `--output`		Output format: json or yaml (default: human-readable)
`--sort-order`	`0`	Sort order in the picker (lower first)
`--supports-images`	`false`	Model accepts image inputs
`--supports-thinking`	`false`	Model supports a thinking/reasoning channel
`--supports-tools`	`true`	Model supports tool calling
`--tier`		Auto-routing tier: expert, think, quick, or empty

ankra ai models delete

Delete a catalog model

ankra ai models delete <id|key> [flags]

Flags

Flag	Default	Description
`--yes`	`false`	Skip the confirmation prompt

ankra ai models list

List the catalog models the chat picker offers

ankra ai models list [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai models reset

Revert the catalog to the built-in defaults

ankra ai models reset [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)
`--yes`	`false`	Skip the confirmation prompt

ankra ai models update

Update a catalog model addressed by its row id or catalog key. Only the flags you pass are changed; the rest keep their current values. Editing a built-in default the first time materialises the catalog.

ankra ai models update <id|key> [flags]

Flags

Flag	Default	Description
`--context-window`	`200000`	Context window in tokens
`--description`		Short description
`--enabled`	`true`	Model is selectable in the picker
`--endpoint`		OpenAI-compatible endpoint id (omit for Ankra-managed Claude)
`--key`		Catalog key (lowercase slug; the model_mode value)
`--max-output`	`8192`	Maximum output tokens
`--model-id`		Provider model id (e.g. claude-opus-5 or gpt-4o)
`--name`		Display name shown in the picker
`-o`, `--output`		Output format: json or yaml (default: human-readable)
`--sort-order`	`0`	Sort order in the picker (lower first)
`--supports-images`	`false`	Model accepts image inputs
`--supports-thinking`	`false`	Model supports a thinking/reasoning channel
`--supports-tools`	`true`	Model supports tool calling
`--tier`		Auto-routing tier: expert, think, quick, or empty

ankra ai openai

Manage the legacy single OpenAI-compatible endpoint configuration. For multiple endpoints and per-model routing prefer ‘ankra ai endpoints’ and ‘ankra ai models’; this command configures the single legacy endpoint the ‘openai_compatible’ provider uses.

ankra ai openai delete

Remove the legacy OpenAI-compatible endpoint

ankra ai openai delete [flags]

Flags

Flag	Default	Description
`--yes`	`false`	Skip the confirmation prompt

ankra ai openai set

Store the legacy OpenAI-compatible endpoint

ankra ai openai set [flags]

Flags

Flag	Default	Description
`--api-key`		API key for the endpoint
`--base-url`		OpenAI-compatible base URL
`--model`		Model id to use
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai openrouter

Manage the organisation’s OpenRouter API key (bring your own key). Store a key with ‘set’, then activate it with ‘ankra ai provider openrouter’. Removing the key while OpenRouter is the active provider resets the organisation to the Ankra-managed default.

ankra ai openrouter remove

Remove the organisation’s OpenRouter API key. When OpenRouter is the active provider the organisation falls back to the Ankra-managed default.

ankra ai openrouter remove [flags]

Flags

Flag	Default	Description
`--yes`	`false`	Skip the confirmation prompt

ankra ai openrouter set

Store and validate an OpenRouter API key (must start with sk-or-). Pass the key with --api-key, pipe it on stdin, or omit both to be prompted interactively. The interactive prompt masks the input; the key is never echoed or logged.

ankra ai openrouter set [flags]

Flags

Flag	Default	Description
`--api-key`		OpenRouter API key (starts with sk-or-; omit to read stdin or be prompted)
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai provider

Set the active AI provider for the organisation.

ankra              Ankra-managed Claude models (the default).
anthropic          Your own Anthropic API key (set it first with 'ankra ai anthropic set').
openai_compatible  Your OpenAI-compatible endpoint (set it first with 'ankra ai openai set').
openrouter         Your own OpenRouter API key (set it first with 'ankra ai openrouter set').

ankra ai provider <ankra|anthropic|openai_compatible|openrouter> [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai remediation

Read the organisation’s AI auto-remediation settings. Auto-remediation is the lane where an alert trigger opens an AI run that may change the platform on its own. Its envelope lives in one policy document: how much the run may do unattended, which tools are exempt from the approval card, and which clusters it is allowed to touch. The policy is read-only from the CLI. Changing it is an organisation-admin action in the portal.

ankra ai remediation policy

Show the organisation’s auto-remediation policy. An organisation that never saved a policy is not an error: the platform answers its own defaults, and this command says so rather than presenting them as a decision somebody made. Two lines carry most of the risk. A per-tool override of ‘auto’ means that tool executes with no approval card at all, and a cluster allow list that was never set means every cluster is in scope, including Ankra’s own.

ankra ai remediation policy [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

ankra ai status

Show the active AI provider and configured credentials

ankra ai status [flags]

Flags

Flag	Default	Description
`-o`, `--output`		Output format: json or yaml (default: human-readable)

​ankra ai

​ankra ai anthropic

​ankra ai anthropic delete

​ankra ai anthropic set

​ankra ai autonomy

​ankra ai autonomy pause

​ankra ai autonomy resume

​ankra ai autonomy start-all

​ankra ai autonomy status

​ankra ai autonomy stop-all

​ankra ai board-identity

​ankra ai board-identity provision

​ankra ai board-identity revoke

​ankra ai board-identity status

​ankra ai endpoints

​ankra ai endpoints create

​ankra ai endpoints delete

​ankra ai endpoints discover

​ankra ai endpoints list

​ankra ai endpoints update

​ankra ai lanes

​ankra ai lanes clear

​ankra ai lanes list

​ankra ai lanes set

​ankra ai models

​ankra ai models create

​ankra ai models delete

​ankra ai models list

​ankra ai models reset

​ankra ai models update

​ankra ai openai

​ankra ai openai delete

​ankra ai openai set

​ankra ai openrouter

​ankra ai openrouter remove

​ankra ai openrouter set

​ankra ai provider

​ankra ai remediation

​ankra ai remediation policy

​ankra ai status

ankra ai

ankra ai anthropic

ankra ai anthropic delete

ankra ai anthropic set

ankra ai autonomy

ankra ai autonomy pause

ankra ai autonomy resume

ankra ai autonomy start-all

ankra ai autonomy status

ankra ai autonomy stop-all

ankra ai board-identity

ankra ai board-identity provision

ankra ai board-identity revoke

ankra ai board-identity status

ankra ai endpoints

ankra ai endpoints create

ankra ai endpoints delete

ankra ai endpoints discover

ankra ai endpoints list

ankra ai endpoints update

ankra ai lanes

ankra ai lanes clear

ankra ai lanes list

ankra ai lanes set

ankra ai models

ankra ai models create

ankra ai models delete

ankra ai models list

ankra ai models reset

ankra ai models update

ankra ai openai

ankra ai openai delete

ankra ai openai set

ankra ai openrouter

ankra ai openrouter remove

ankra ai openrouter set

ankra ai provider

ankra ai remediation

ankra ai remediation policy

ankra ai status