DigestAI news desk

Cut through the AI noise.

Agents & Tools4 min read

Parcha Labs releases AgentRun DSL beta for building agent workflows

Parcha Labs, Inc. announced the beta release of AgentRun, a domain‑specific language that lets developers turn AI agents into repeatable workflows. The initial version, 0.1.0‑beta.4, runs on Node 22.19+ and can be installed with npm packages @parcha/agentrun-dsl@beta and @parcha/agentrun-jev@beta. AgentRun lets users define steps in JSON or TypeScript, embed Jev‑powered decision nodes, and call…

1 source primary source HN 41

Key points

  • Parcha Labs released AgentRun DSL version 0.1.0‑beta.4 for defining repeatable agent workflows
  • The tool integrates Jev decisions, Pi extension, and runs on Node 22.19+ with npm install commands
  • Workflows can be written in JSON or TypeScript, support parallel mapping, loops, and escalation paths

The toolkit includes a Pi extension (version 0.87.0) that lets the Pi model build, inspect, and execute workflows directly from a chat session. Example demos cover ticket‑routing and scripted research, all without requiring an API key for the demo runs. Workflows support parallel mapping, bounded loops, escalation paths, and runtime state validation. The code and documentation are released under the Apache‑2.0 license, with contributions from Grep.ai, and the project is hosted on GitHub.

AgentRun aims to simplify the orchestration of LLM‑driven agents for developers, offering typed contracts, sandboxed execution, and easy integration into existing toolchains.

Full story from github.com · via Hacker News primary sourceOpen source ↗

Show HN: AgentRun: DSL to turn agents into workflows

github.com · 23 September 2026

Loading the full article…

This text was published by github.com. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

1source
Topics · follow one to build your own front page
Parcha Labs, Inc.Grep.ai

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Agents & Tools

All →

Related stories