Agency Swarm Model Card
这是可索引项目报告证据页：它保留 Agency Swarm 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。
Agency Swarm Model Card
| Field | Value |
|---|---|
| Repository | VRSEN/agency-swarm |
| Category | OpenAI Agents SDK Swarm Orchestrator |
| Stars / forks snapshot | 4,445 / 1,058 |
| Commits / issues / PRs snapshot | 2,545 / 0 / 6 |
| Language | Python |
| License | MIT |
| Latest visible dated signal | 2026-06-12 GitHub API snapshot |
| Raw capture | raw-github/vrsen_agency-swarm.md |
| Updated by | hourly public metadata update, 2026-06-13 02:15 +0800 |
1. Role in Self Evolve
Agency Swarm is a mature Python orchestration framework that layers role-aware communication flows, type-safe tools, thread persistence, and terminal/web demos on top of the OpenAI Agents SDK. It matters because self-evolving agents need explicit runtime, memory, skill, and benchmark substrates before their improvement claims become trustworthy.
2. Working Principle
define agents and directional communication flows -> attach function tools and persistence callbacks -> route work through agency-level orchestration -> reuse terminal/web demos and docs as reproducible multi-agent operating patterns
3. Evidence Path
GitHub GraphQL/API snapshot captured via authenticated gh on 2026-06-13 showed 4,445 stars, 1,058 forks, 0 open issues, 6 open pull requests, 2,545 commits on main, latest push at 2026-06-12T00:13:04Z, MIT license, and latest release v1.10.1 published on 2026-06-11. The snapshot also showed 64 releases with v1.10.1 latest on 2026-06-11. This run keeps freshness honest because it uses authenticated GitHub API data rather than stale local summaries.
4. Teaching Use
Use this card to explain OpenAI Agents SDK Swarm Orchestrator: it shows how swarm runtimes, skill optimizers, benchmark suites, browser harnesses, and memory middleware fit into the broader 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 GitHub API snapshot signals unless independently revalidated later.