Connect OpenClaw to Parallel

Run a one-shot web search returning ranked URLs with LLM excerpts.

Extract clean markdown excerpts from a list of URLs.

Start a deep-research / enrichment task run.

Retrieve a task run object and its status.

Retrieve a completed task run result (blocks until the run finishes or timeout expires).

Retrieve the original input submitted for a task run.

Stream real-time progress events for an individual task run via SSE.

Create a batch group to run many task runs together.

Add one or more task runs to an existing group.

List runs in a task group.

Stream real-time events for a task group while runs are active (SSE).

Retrieve a task group's status and aggregate progress.

Retrieve a single run within a task group.

Discover verified entities matching plain-language criteria.

Transform a natural-language objective into a structured FindAll spec (suggested starting point).

Poll a FindAll run's status.

Get discovered entities / candidates for a FindAll run.

Add column enrichments to a FindAll run's discovered entities.

Find more entities beyond the original match limit.

Cancel an in-progress FindAll run.

Synchronous real-time people / company lookup.

Set up continuous web tracking.

List monitors (cursor pagination).

Retrieve a single monitor.

Update a monitor's config.

List detected change events for a monitor.

Manually trigger a monitor check now.

Stop / cancel a monitor.

Simulate a monitor event to test webhook delivery without waiting for a real run.

OpenAI-compatible chat completion backed by Parallel web research (Beta).