Intake notes: listed with facts from the source repo; not yet vetted. A verdict waits on a real hands-on audit (install, run, audit what it injects). Health is checked automatically; the summary is the author’s own description.
openai-agents
• Not yet vettedA lightweight framework for multi-agent workflows, from OpenAI.
In the intake queue. Listed with facts only; no verdict until a human runs it.
by openai agent framework Orchestration
Shipped today passing liveness · checked Jul 28, 2026
Commit activity · last 52 weeks
Stars28k
LanguagePython
LicenseMIT
Open issues51
Pricingfree
ListedJul 12, 2026
Facts pulled from the source repo and refreshed nightly. Stars are a data point, not our ranking. We don't order by popularity.
Runs in
| Harness | Support | Notes |
|---|---|---|
| Claude Code | untested | — |
Support levels reflect what we actually ran, not what the README claims. untested means exactly that.
What a vet will check
- What it installs and its dependency footprint
- Whether it needs metered API keys to run
- How it sits alongside Claude Code rather than replacing it
No verdict is published until a human installs it, runs it, and audits what it injects. How vetting works →
More in Orchestration
mastra agent framework Mastra is the modern TypeScript framework for AI-powered applications and agents.
pydantic-ai agent framework AI Agent Framework, the Pydantic way
zen-mcp-server MCP server Routes work to other models (Gemini, GPT, local) as second opinions inside one session: extended reasoning, review, and consensus workflows.