Trigger
Build and deploy fully-managed AI agents and workflows with durable tasks, queues, observability, and elastic scaling. Designed for developers who need reliable, long-running processes.
Trigger.dev
Trigger.dev is the open source platform for building AI workflows in TypeScript. It enables developers to create durable, long-running tasks with built-in retries, queues, observability, and elastic scaling. Whether you need to process media, run scheduled tasks, or build AI agents with human-in-the-loop workflows, Trigger.dev provides the infrastructure to keep your processes alive through refreshes, redeploys, and crashes.
Key Features
- Durable AI Agents: Build agents that survive refreshes, redeploys, and crashes with full state persistence
- Human-in-the-Loop: Implement approval workflows and manual interventions within automated processes
- Real-time Streaming: Stream results directly to your frontend without API routes
- Concurrency & Queues: Control task execution with configurable concurrency limits and queue management
- Scheduled Tasks: Durable cron schedules that persist across restarts and timeouts
- Observability & Monitoring: Real-time tracing, logging, and monitoring of all workflows
- Tool Calling: Native support for function calling and external tool integration
- Multi-language Support: Run tasks in TypeScript, Python, and other languages
- Self-hosting: Deploy Trigger.dev on your own infrastructure
- MCP Server Integration: Connect with Model Context Protocol servers for enhanced capabilities
Tech / Self-Hosting
Trigger.dev is built with TypeScript and supports self-hosting for full control over your data and infrastructure. The platform is designed for elastic scaling, automatically adjusting resources based on workload demands. Documentation covers quick start guides, framework-specific implementations (Node.js, Next.js, Bun, Remix), and detailed self-hosting instructions.
Supported Runtimes: TypeScript, Python, Bun, Node.js Deployment Options: Cloud-hosted (managed) or self-hosted Integration: Works with Anthropic, OpenAI, and other LLM providers Observability: Built-in tracing, metrics, and logging Scalability: Automatic scaling based on task volume and complexity