Utah Model Card
这是可索引项目报告证据页：它保留 Utah Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
Utah Model Card
| Field | Value |
|---|---|
| Repository | inngest/utah |
| Category | Event-Driven Agent Harness Runtime |
| Stars / forks snapshot | 116 / 2 |
| Language | TypeScript |
| License | Apache-2.0 |
| Raw capture | raw-github/inngest_utah.md |
| Updated by | hourly public metadata update, 2026-05-26 10:04 +0800 |
1. Role in Self Evolve
Utah is a universally triggered agent harness built on Inngest events with durable retries and local worker execution for think-act-observe loops. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
incoming event -> think/act/observe loop -> durable retries and singleton control -> memory/session trace updates -> channel response
3. Evidence Path
web-observed GitHub page showed 116 stars, 2 forks, 41 commits, Apache-2.0 license, and README language for durable event-driven execution with retry/cancel behavior, channel adapters, skills, file-based memory, and workspace eval traces. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Event-Driven Agent Harness Runtime: it shows how harness/runtime/benchmark layers convert agent behavior into reproducible and auditable engineering workflows.
5. Limits
The repository was not cloned in this iteration; no benchmark run, plugin install, workflow execution, or agent loop experiment was executed. Counts and claims are visible public-page/search signals unless independently revalidated later.