Claude Agent SDK vs OpenAI Agents SDK
Claude Agent SDK (Anthropic) and OpenAI Agents SDK (OpenAI) side by side on public data, as of Nov 20, 2026.
Claude Agent SDK has 4.1x the weekly package downloads of OpenAI Agents SDK (29.3M against 7.2M). OpenAI Agents SDK has 3.6x the GitHub stars of Claude Agent SDK (30.8K against 8,588). Over the last 30 days downloads moved +38% for Claude Agent SDK and +39% for OpenAI Agents SDK. Claude Agent SDK shipped 41 stable releases in the past 90 days. OpenAI Agents SDK shipped 7 stable releases in the past 90 days.
Which should you choose?
Choose Claude Agent SDK if
- you want frequent updates (41 stable releases in 90 days against 7)
Built from documented features, official prices, status pages and usage data on this page; it does not judge output quality.
Side-by-side numbers
| Metric | Claude Agent SDK | OpenAI Agents SDK |
|---|---|---|
| Gid Score | 64 | 62 |
| Usage data as of | Nov 19 | Nov 19 |
| Rank by Gid Score | #4 | #6 |
| Downloads, last 7 days | 29.3M | 7.2M |
| Downloads, 7-day change | up 5.9% | up 4.8% |
| Downloads, 30-day change | up 37.6% | up 38.9% |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 8,588 | 30.8K |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 8 | 5 |
| Latest stable release | 0.2.185 · yesterday | 0.25.0 · 2d ago |
| Stable releases, 90 days | 41 | 7 |
| Terminal-Bench (best run) | — | — |
| Price | Free (OSS) | Free (OSS) |
| Incidents, last 30 days | 12 · 10 major or critical | — |
| License | MIT (Python SDK) | MIT |
| First released | — | March 2025 |
| Interfaces | Python library, TypeScript library | Python library, TypeScript library |
| Models | — | — |
A dash means there is no public data for that metric as of Nov 20, 2026.
Trends
Claude Agent SDK
Anthropic's SDK that exposes the agent loop, tools and context management behind Claude Code, for building custom agents in Python and TypeScript.
Pricing: The SDK is free to install; usage is billed through the Claude API or a Claude subscription.
Latest release 0.2.185:
- bash pip install claude-agent-sdk==0.2.185
OpenAI Agents SDK
OpenAI's lightweight framework for multi-agent workflows, with handoffs, guardrails, sessions and tracing. Available for Python and TypeScript. Per its PyPI page it is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs as well as 100+ other LLMs.
Pricing: OpenAI Agents SDK is open source and free to use; you pay only for the models and infrastructure it runs on.
Latest release 0.25.0:
- Migrate Runloop workloads to another supported sandbox provider, such as Modal, or remain on 0.24.0 while migrating. Provider-specific sessions and snapshots require a separate data migration.
- Resume nested agent-tool approvals with output guardrails using RunState schema 1.22. Pydantic checkpoints now preserve default values and in-place edits.
- OpenAIResponsesCompactionSession now defaults to gpt-6-luna. Set model="gpt-4.1" to keep the previous choice. Agent model settings also follow the selected model more closely.
- Runner handoffs can opt into recovery with failure_error_function. Omitting it preserves exception propagation. The demo REPL can now approve or reject individual tool calls.