AutoR Model Card
这是可索引项目报告证据页：它保留 AutoR 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。
AutoR Model Card
| Field | Value |
|---|---|
| Repository | AutoX-AI-Labs/AutoR |
| Category | Human-Centered Research Harness |
| Stars / forks snapshot | 897 / 22 |
| Language | Python |
| License | Public repository license not verified |
| Raw capture | raw-github/autox-ai-labs_autor.md |
| Updated by | hourly public metadata update, 2026-05-26 09:12 +0800 |
1. Role in Self Evolve
AutoR is a terminal-first research harness where AI handles execution, humans retain direction, and every run is stored as an inspectable artifact on disk. It matters because self-evolving agents need reliable harnesses, memory/skill surfaces, feedback evidence and benchmark loops before any improvement claim can be trusted.
2. Working Principle
human research intent -> staged agent execution -> approval checkpoints -> artifact-backed run directory -> resume/redo/rollback
3. Evidence Path
web-observed GitHub page showed 897 stars, 22 forks, 154 commits, Python primary language, no releases, and README language about a 9-stage workflow, human approval, local browser Studio, reproducible runs and rollback-stage recovery. 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 Human-Centered Research Harness: it shows which part of the agent improvement stack is made operational, and where evaluator, policy, memory, skill, task-state or artifact evidence enters the loop.
5. Limits
The repository was not cloned in this iteration; no benchmark, install flow, workflow run, policy audit, memory experiment, OpenClaw run, or agent loop was executed. Counts and claims are visible public-page/search signals unless independently revalidated later.