Back to Continue

Agents

docs/agents/overview.mdx

1.5.453.4 KB
Original Source

Agents use the same markdown file format as checks. The difference: agents can be triggered by events beyond PR open — cron schedules, GitHub issues, Sentry alerts, Slack messages, webhooks. Triggers are configured in Mission Control.

Local agents vs. cloud agents

There are two ways to define agents:

  • Local: Place agent files in .continue/agents/ in your repository. Version-controlled and shared with your team.
  • Cloud: Created and managed on continue.dev/agents. Web UI for configuration, no file to commit.

Both run on Continue's cloud infrastructure.

Triggers

Triggers determine when an agent runs. They are configured in Mission Control.

Supported trigger types:

TriggerDescription
CronRun on a schedule (daily, weekly, hourly, custom)
WebhookRun when an external system sends a request
GitHub eventRun when specific GitHub events occur (PR opened, issue created, label added, etc.)
<Note> Version-controlled trigger configuration (defined in the agent file itself) is on the roadmap. Today, all triggers are managed through Mission Control. </Note>

Running agents

<Tabs> <Tab title="Mission Control"> Trigger agents from the web interface at [continue.dev](https://continue.dev) and review results in real-time. </Tab> <Tab title="CLI interactive"> ```bash cn --agent my-org/my-agent ```
Opens an interactive chat session with the agent.
</Tab> <Tab title="CLI headless"> ```bash cn -p --agent my-org/my-agent "Run weekly security scan" ```
Runs the agent non-interactively. Useful for CI/CD pipelines and scheduled automation.
</Tab> </Tabs>

Checks vs. agents

ChecksAgents
File location.continue/checks/.continue/agents/ or continue.dev
TriggerAlways on PR openConfigurable in Mission Control
PurposePass/fail review of PRsAny automated task

Pre-configured agents you can use immediately:

<CardGroup cols={2}> <Card title="Security Scanning" icon="shield-check" href="https://continue.dev/continuedev/snyk-continuous-ai-agent"> `continuedev/snyk-continuous-ai-agent`
Monitors vulnerabilities and automatically opens PRs with fixes.
</Card> <Card title="GitHub Management" icon="github" href="https://continue.dev/continuedev/github-project-manager-agent"> `continuedev/github-project-manager-agent`
Triages issues and manages project workflows.
</Card> <Card title="Analytics Insights" icon="chart-bar" href="https://continue.dev/continuedev/posthog-continuous-ai-agent"> `continuedev/posthog-continuous-ai-agent`
Analyzes user data and creates actionable tasks.
</Card> <Card title="Performance Optimization" icon="gauge-high" href="https://continue.dev/continuedev/netlify-continuous-ai-agent"> `continuedev/netlify-continuous-ai-agent`
Monitors Core Web Vitals and optimizes deployments.
</Card> <Card title="Database Auditing" icon="database" href="https://continue.dev/continuedev/supabase-agent"> `continuedev/supabase-agent`
Audits RLS security and generates migrations.
</Card> <Card title="Data Pipelines" icon="arrows-rotate" href="https://continue.dev/continuedev/dlt-agent"> `continuedev/dlt-agent`
Inspects pipelines and debugs load errors.
</Card> </CardGroup>