inferablehq/inferable

Build reliable AI Workflows and Agents with humans in the loop, structured outputs and durable execution.

56
/ 100
Established

This project helps operations engineers, product managers, or customer support leads create reliable AI-powered workflows that involve human checks. You feed it raw text or data, and it outputs structured information or a completed action, incorporating necessary approvals via Slack or email. It's designed for anyone who needs to automate complex processes where AI analysis needs to be reviewed or validated by a human before proceeding.

435 stars. Available on npm.

Use this if you need to build AI applications that involve step-by-step human approval, ensure consistent data formatting from AI, and require long-running, fault-tolerant processes.

Not ideal if your AI tasks are simple, don't require human intervention, or don't involve long-running, multi-step workflows.

AI-automation workflow-orchestration human-in-the-loop customer-support-automation content-moderation
Maintenance 6 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 15 / 25

How are scores calculated?

Stars

435

Forks

35

Language

TypeScript

License

MIT

Category

llm-api-gateways

Last pushed

Nov 24, 2025

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/inferablehq/inferable"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.