Status basis: npm_downloads_7d gained 116 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 116 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 116 per 3d from 646 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 646 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 529 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 529 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -117 per 3d from 148 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -20 per 3d from 105 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -7 per 3d from 92 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -155 per 3d from 92 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 105 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 275.0 is 5.5 standard deviations from this entity's own prior mean (-19.2±53.1, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 92 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -183 per 3d from 87 (<= 40% of the prior window)
- Anomaly daily change 275.0 is 5.5 standard deviations from this entity's own prior mean (-19.2±53.1, baseline excludes this point) — unusual, not necessarily adoption
- Cooling hn_points momentum fell to 0 per 3d from 13 (<= 40% of the prior window)
- Cooling hn_points momentum fell to 2 per 3d from 41 (<= 40% of the prior window)
- first observed Kanon started keeping permanent history for this agent
| Machine-callable | — | unknown | — |
| Open source | 1 | inferred | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | — | unknown | — |
| Autonomy level | — | unknown | — |
| Pricing model | — | unknown | — |
| Integrations | — | unknown | — |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
It provides a practical abstraction layer that bridges the gap between experimental agents and production-ready systems.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“npm install @parcha/agentrun-dsl@beta”— readme
“Define repeatable steps, use [Jev] for focused decisions”— readme
FAQ
What is AgentRun?
AgentRun is a domain-specific language that enables developers to turn AI agents into structured, repeatable workflows.
What does AgentRun do?
Developers need a simple way to organize AI agents into reliable, executable workflows for production use.
Why does AgentRun matter?
It provides a practical abstraction layer that bridges the gap between experimental agents and production-ready systems.
Is AgentRun open source?
Yes — AgentRun is open source.
Can I self-host AgentRun?
Yes — AgentRun can be self-hosted.
How popular is AgentRun?
As tracked by KanonAgent: 51 upvotes (first indexed 2026-09-23).
What are the best AgentRun alternatives?
Similar AI agents tracked by KanonAgent: AEO Engine, langchain, BIG, autogen, Indexsy, POST BRIDGE.