AgentRun
DSL to turn agents into workflows
AgentRun (agent.run()) is a workflow language for the AI agents you already run. You define repeatable steps, use Jev for focused decisions, and call an agent only when the work needs investigation, while your app keeps its own tools, model access, permissions and budgets. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49821438
✨ The overview, FAQ and details below were drafted by AI from the product's own website and haven't been reviewed by the maker yet. Are you the maker? Claim this listing to review and edit them.
Overview
Who is it for?
Developers who want predictable, repeatable workflows around their AI agents.
Problem
Letting an agent handle every step of a process is costly and unpredictable.
Solution
A DSL that mixes scripted steps, small typed decisions and agent calls, with demos that run without an API key.
What makes it unique
Decisions and agent calls are explicit steps in the workflow, so the agent is used only where it adds value.
AgentRun FAQ
How do I try it?
Run npm install @parcha/agentrun-dsl@beta and then npx agentrun demo; it needs Node 22.19+.
Do the demos need an API key?
No, the demos use scripted decisions and responses.
Details
- Pricing
- Open Source
- Categories
- AI AgentsCoding & Dev Tools
- Built for
- Developers
- Platforms
- CLI
- Tech stack
- TypeScriptNode.js
Compare AgentRun
Hunted by AI Launch Team
Discussion (0)
Sign in to join the discussion.