OpenCrabs Model Card
这是可索引项目报告证据页：它保留 OpenCrabs 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。
OpenCrabs Model Card
| Field | Value |
|---|---|
| Repository | adolfousier/opencrabs |
| Category | Self-Improving Terminal Agent |
| Stars / forks snapshot | 755 / 72 |
| Language | Rust |
| License | MIT |
| Raw capture | raw-github/adolfousier_opencrabs.md |
| Updated by | hourly public metadata update, 2026-05-24 |
1. Role in Self Evolve
OpenCrabs 是受 OpenClaw 启发的单二进制多渠道 AI agent，强调本地 brain files、memory search、custom commands、cron/background jobs 和 self-update 组成的自改进循环。
2. Working Principle
local brain files -> procedural/episodic memory -> hybrid recall -> commands/tools/channels -> self-update hooks
3. Evidence Path
web GitHub page observed MIT license, Rust primary language, 121 releases with v0.3.27 latest on 2026-05-23, local brain/memory/command self-improvement mechanics, 755 stars and 72 forks. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Self-Improving Terminal Agent in the raw -> classification -> project card -> site/report pipeline. The reading path is: raw capture -> classification row -> public site card -> project report -> aggregate GitHub analysis.
5. Limits
当前未克隆源码，未运行 benchmark、SDK examples、skill install flows 或 memory experiments；star/fork/commit 快照来自公开 GitHub 页面文本或可见页面片段。