agentic-stack Model Card
这是可索引项目报告证据页：它保留 agentic-stack 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。
agentic-stack Model Card
| Field | Value |
|---|---|
| Repository | codejunkie99/agentic-stack |
| Category | Portable Agent Memory and Skills Layer |
| Stars / forks snapshot | 2000 / 254 |
| Language | Python |
| License | Apache-2.0 |
| Raw capture | raw-github/codejunkie99_agentic-stack.md |
| Updated by | hourly public metadata update, 2026-05-25 09:19 +0800 |
1. Role in Self Evolve
agentic-stack 把 memory、skills、protocols 和 harness adapters 放进可迁移的 .agent/ 层，让 Claude Code、Cursor、OpenClaw、Codex、Gemini、Hermes 等工具共享同一套经验与技能。
2. Working Principle
portable .agent workspace -> adapters for agent harnesses -> local data layer -> memory/skills/protocol transfer -> flywheel artifacts
3. Evidence Path
web GitHub page observed 162 commits, Apache-2.0 license, 2k stars and 254 forks; README says a portable .agent folder carries memory, skills and protocols across Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, GitHub Copilot CLI, Gemini CLI, Hermes, Pi Coding Agent, Codex and Antigravity, plus local dashboards and approved run artifacts. Shell GitHub API access remained DNS-blocked in this run, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Portable Agent Memory and Skills Layer 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、skill install flows、memory experiments、MCP servers、agent evolution loops、security scanners 或 production deployments；star/fork/commit/release 快照来自公开 GitHub 页面文本或可见页面片段。