swarmclaw Model Card
这是可索引项目报告证据页：它保留 swarmclaw 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。
swarmclaw Model Card
| Field | Value |
|---|---|
| Repository | swarmclawai/swarmclaw |
| Category | Self-Hosted Agent Runtime |
| Stars / forks snapshot | 544 / 106 |
| Commits / issues / PRs snapshot | 490 / 3 / 0 |
| Language | TypeScript |
| License | MIT |
| Raw capture | raw-github/swarmclawai_swarmclaw.md |
| Updated by | hourly public metadata update, 2026-06-04 15:36 +0800 |
1. Role in Self Evolve
swarmclawai/swarmclaw is a self-hosted multi-agent runtime that combines memory, MCP tooling, delegation, schedules, skills, and swarm-oriented execution surfaces. It matters because self-evolving agents need inspectable memory, skill, harness, benchmark, and runtime substrates before improvement claims become trustworthy.
2. Working Principle
agent runtime -> memory and MCP connectors -> schedules and delegation -> swarm workflows -> self-hosted distribution and release cadence
3. Evidence Path
web-observed GitHub page showed 544 stars, 106 forks, 490 commits, 3 open issues, 0 pull requests, and a self-hosted multi-agent runtime that exposes memory, MCP tools, schedules, delegation, skills, and 23+ model providers. This iteration keeps freshness honest: the snapshot comes from the public GitHub page observed on 2026-06-04, while shell GitHub API access remained blocked in this workspace.
4. Teaching Use
Use this card to explain Self-Hosted Agent Runtime: it shows how raw public GitHub evidence becomes a project-facing teaching artifact inside the self-evolving-agent pipeline.
5. Limits
The repository was not cloned in this iteration; no benchmark run, workflow execution, or agent loop experiment was executed. Counts and claims are visible public-page signals unless independently revalidated later.