ACPX Model Card
这是可索引项目报告证据页：它保留 ACPX 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。
ACPX Model Card
| Field | Value |
|---|---|
| Repository | openclaw/acpx |
| Category | State-Preserving Agent Runtime and Session Handoff |
| Stars / forks snapshot | 2800 / 272 |
| Language | TypeScript |
| License | MIT |
| Raw capture | raw-github/openclaw_acpx.md |
| Updated by | hourly public metadata update, 2026-05-30 01:15 +0800 |
1. Role in Self Evolve
acpx is OpenClaw’s state-preserving runtime for switching across coding agents while retaining full session context and ACP compatibility. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
preserve session state across agent switches -> coordinate skills through ACP-compatible runtime contracts -> maintain continuity for long-running workflows -> turn ad hoc tool use into transferable orchestration assets
3. Evidence Path
web-observed GitHub page showed about 2.8k stars, 272 forks, 411 commits, MIT license, and about text stating acpx preserves complete session context when switching between coding agents. 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 State-Preserving Agent Runtime and Session Handoff: 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.