# Parcha-ai/agentrun

> AgentRun is a DSL for describing repeatable AI agent workflows: steps, tool calls, Jev-based decisions, and escalation for review. Your application keeps its own tools, model access, permissions, and budgets.

- Magnitude: 1.5 out of 10 — Steady
- Stars: 3 total · +3 stars today
- Star trust: star growth looks organic
- Category: AI agents · Language: JavaScript · License: Apache-2.0 · Created: 2026-09-23 · Last push: 2026-09-23
- GitHub: https://github.com/Parcha-ai/agentrun · Page: https://gitnova.dev/en/r/Parcha-ai/agentrun

## Useful for

- Define support ticket routing as a workflow with answer checks and escalation
- Wire your own tools and agent through runEffect and runNode adapters
- Build a workflow in the Pi extension to research a repository with parallel subtasks

## Why it’s here

- 3 stars today.
- The repository is 0 days old and already has 3 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Show HN: AgentRun: DSL to turn agents into Workflows” — 8 points, 2 h ago.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1
- Issues and pull requests: 14
- Watchers: 0
- Average over the last week: 3 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 4 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-23: 0, 0, 0, 3

## Hacker News

- Show HN: AgentRun: DSL to turn agents into Workflows — 8 points, 0 comments: https://news.ycombinator.com/item?id=49821438

## Spotted in now

- Spotted on Hacker News

## More in this category

1. **google/ax** — 8.8 · Breakout · AI agents · Go · +977 stars today
   A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and restricts network…
   Full card: https://gitnova.dev/en/r/google/ax.md
2. **unreallabsai/unreal-agent** — 8.7 · Breakout · AI agents · Go · +444 stars today
   Async-first agent harness in Go: sessions with persisted forkable history, input deduplication, an LLM-turn coordinator, and asynchronous operation execution via swappable components.
   Full card: https://gitnova.dev/en/r/unreallabsai/unreal-agent.md
3. **NandhaKishorM/laya** — 8.6 · Breakout · AI agents · Python · +2,434 stars today
   Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
   Full card: https://gitnova.dev/en/r/NandhaKishorM/laya.md
4. **jev-chat/jev-chat-jarvis** — 8.0 · Breakout · AI agents · Kotlin · +667 stars today
   Android app that reads the on-screen chat via AccessibilityService, judges the other side's intent with the Jev model, and shows 3 ranked reply drafts in a translucent overlay. Replies are filled into the input box but sent manually.
   Full card: https://gitnova.dev/en/r/jev-chat/jev-chat-jarvis.md
5. **CopilotKit/openmuse** — 7.8 · Breakout · AI agents · TypeScript · +550 stars today
   A personal AI agent with a browser, terminal, and files that carries out tasks on request and shows its work. Built with CopilotKit and AG-UI for iOS, Android, and web.
   Full card: https://gitnova.dev/en/r/CopilotKit/openmuse.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-23 22:36 UTC, updated every 30 minutes.