Trellis Model Card
这是可索引项目报告证据页：它保留 Trellis 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。
Trellis Model Card
| Field | Value |
|---|---|
| Repository | mindfold-ai/trellis |
| Category | Agent Harness and Local/Cloud Runtime Framework |
| Stars / forks snapshot | 8600 / 468 |
| Language | TypeScript |
| License | AGPL-3.0 |
| Raw capture | raw-github/mindfold-ai_trellis.md |
| Updated by | hourly public metadata update, 2026-05-28 22:03 +0800 |
1. Role in Self Evolve
Trellis is an open-source harness for running and coordinating AI agents across local and cloud environments with practical workflow execution support. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
agent session planning -> deterministic harness/tool execution -> local/cloud runtime handoff -> human or evaluator feedback loop for iterative task completion
3. Evidence Path
web-observed GitHub page showed 8.6k stars, 468 forks, 1,017 commits, AGPL-3.0 license, and README positioning as an agent harness. 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 Agent Harness and Local/Cloud Runtime Framework: 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.