OpenAI Agents SDK (JS) Model Card
这是可索引项目报告证据页：它保留 OpenAI Agents SDK (JS) 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。
OpenAI Agents SDK (JS) Model Card
| Field | Value |
|---|---|
| Repository | openai/openai-agents-js |
| Category | Official OpenAI Agents SDK TypeScript Baseline |
| Stars / forks snapshot | 3,203 / 809 |
| Commits / issues / PRs snapshot | 933 / 35 / 29 |
| Language | TypeScript |
| License | MIT |
| Latest visible dated signal | 2026-06-12 GitHub API snapshot |
| Raw capture | raw-github/openai_openai-agents-js.md |
| Updated by | hourly public metadata update, 2026-06-13 02:15 +0800 |
1. Role in Self Evolve
OpenAI Agents SDK (JS) is the official TypeScript baseline for building agent orchestration loops with tools, handoffs, guardrails, realtime hooks, and tracing. It matters because third-party swarm, harness, memory, and skill claims need a canonical upstream orchestration/runtime baseline before they can be compared honestly.
2. Working Principle
compose agents in TypeScript -> attach tools, handoffs, and realtime transport -> trace execution and guardrails -> use the official JS runtime as the canonical baseline for browser, frontend, and full-stack swarm orchestration claims
3. Evidence Path
GitHub GraphQL/API snapshot captured via authenticated gh on 2026-06-13 showed 3,203 stars, 809 forks, 35 open issues, 29 open pull requests, 933 commits on main, latest push at 2026-06-12T08:33:10Z, MIT license, and latest release v0.11.6 published on 2026-05-29. The snapshot also showed 56 releases with v0.11.6 latest on 2026-05-29. 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 Official OpenAI Agents SDK TypeScript Baseline: it gives the corpus a canonical upstream baseline for agent orchestration, guardrails, tracing, and tool/handoff design before downstream systems add their own memory, benchmark, or self-improvement layers.
5. Limits
The repository was not cloned or executed in this iteration; no SDK example, agent loop, benchmark, or realtime flow was run locally. Counts and claims are GitHub API snapshot signals unless independently revalidated later.