Hatchet

Durable task orchestration for agents and background jobs

Deployment Code Execution ObservabilityCLI

Hatchet is an open-source orchestration platform for AI agents, durable workflows, and background tasks. It provides retries, concurrency and rate limits, scheduling, event triggers, streaming, observability, and failure recovery, with managed cloud or self-hosted deployment and SDKs for TypeScript, Python, Go, and Ruby.

Best for agent capabilities

Code execution Deployment Workflow automation Observability and evaluation

Useful in agent tasks

Build and deploy software

Write, execute, test, and ship code from an agent workflow.

Operate production agents

Secure, observe, evaluate, and improve agents after they ship.

Communicate with users

Send timely, personalized messages and handle conversations across channels.

Automate business workflows

Connect services and coordinate durable multi-step operational work.

Overview

Websitehatchet.run

Authapi key

PricingFree tier available · $0/month (100,000 task runs)

SDKstypescript, python, go, ruby

OpenAPIYes

MCP SupportNo

When to use Hatchet

Hatchet is listed for Deployment, Code Execution, Observability workflows. Hatchet is an open-source orchestration platform for AI agents, durable workflows, and background tasks. It provides retries, concurrency and rate limits, scheduling, event triggers, streaming, observability, and failure recovery, with managed cloud or self-hosted deployment and SDKs for TypeScript, Python, Go, and Ruby. Consider it when an agent needs this capability through a documented service boundary instead of custom infrastructure maintained inside the application.

In 4agent's task model, the product maps to code execution, deployment, workflow automation, observability and evaluation. That makes it a candidate for workflows that build and deploy software, operate production agents, communicate with users, automate business workflows.

Integration checklist

Access: confirm the api key authentication flow, credential scope, rotation process, and whether calls can be attributed to a user or service identity.
Client support: official or documented clients are listed for typescript, python, go, ruby.
Automation: OpenAPI is listed as available, MCP is not currently recorded, and CLI support is listed as available. Confirm each requirement in the provider's current documentation.
Operations: test rate limits, timeouts, retry safety, error payloads, logs, data retention, and the current free-tier and paid pricing model with production-like volume.

Sources and verification

Use these primary sources to verify current behavior before making an implementation or purchasing decision. Product capabilities, limits, and prices can change after a 4agent listing is reviewed.