- 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.
- MCP v2 Streamable HTTP supports concurrent requests. MCP v1 retains serialized requests. Failed and incomplete Responses calls now retain provider-reported token usage.
- expose utilities for third-party session adapters (16fdb20)
OpenAI Agents SDK by OpenAI
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.
Use it in: API / SDK Works with: MCP Multi-agent
On this page
Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number
What OpenAI Agents SDK does
OpenAI Agents SDK is a vendor agent SDK from OpenAI, first released in March 2025. You use it through a Python library and a TypeScript library. Its documentation covers MCP servers and subagents or parallel agents. It can run models from OpenAI and any OpenAI-compatible endpoint. It is used from Python and TypeScript. It is free and open source (MIT); you pay only for the models it calls.
Key facts
| Maker | OpenAI |
|---|---|
| Type | Vendor agent SDK |
| First released | March 2025 |
| License | MIT |
| Interfaces | Python library, TypeScript library |
| Main language | Python |
| Open issues and PRs | 36 |
Pricing
OpenAI Agents SDK is open source and free to use; you pay only for the models and infrastructure it runs on.
Checked Nov 4, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (MIT)
- Where you use itPython library, TypeScript library
- Supports MCP?Yes
- Model providersopenai, any OpenAI-compatible
- Subagents / multi-agent?Yes
- Feature comparisonAll agents
- Closest alternativeLangChain · all alternatives
What's new in OpenAI Agents SDK: October 2026
October brought refinements to sandbox configuration, session management, and tool handling across three releases. The month focused on expanding customization options and improving reliability in core agent operations.
- MCP tools now expose annotations and support run-wide exception formatting for better error handling.
- Sandbox operations gained opt-in Docker removal protection and configurable memory consolidation.
- Session encryption and conversation writes received new budget and batching controls to optimize performance.
- Sensitive trace capture now respects model metadata to improve privacy handling.
3 releases this month · summarised from the official release notes · all months
AgentGid articles about OpenAI Agents SDK
Best AI Agent Frameworks in 2026: LangGraph, CrewAI, OpenAI Agents SDK and More
The AI agent frameworks developers actually use, ranked on live downloads and GitHub data, with a plain guide to which one fits Python, TypeScript, multi-agent or Microsoft-stack work.
LangGraph vs CrewAI vs OpenAI Agents SDK: Which Agent Framework to Use (2026)
Three of the most used agent frameworks compared on design, control, multi-agent support, language support, adoption and release activity, with live data and a decision guide.
How to Build an AI Agent: No-Code Builders, Frameworks and SDKs
A practical guide to building your first AI agent: choosing between no-code builders, open-source frameworks and model vendors' SDKs, the core agent loop, tools, guardrails and testing, with live usage data for each option.
Get started with OpenAI Agents SDK
| npm | npm install @openai/agents |
|---|---|
| PyPI | pip install openai-agents |
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Add-ons for OpenAI Agents SDK: save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for OpenAI Agents SDK or for agent frameworks in general. Savings and results depend on your workload.
OpenAI Agents SDK alternatives
Best OpenAI Agents SDK alternatives compared · All agent frameworks and SDKs
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
79 | 41.1M | up 5.7% | down 2.7% | 150K+76/day | 1.5.22d ago | Free (OSS) | |||
| 2 |
LangGraphLangChain |
75 | 20.1M | up 5.5% | up 29.2% | 45.1K+48/day | 1.2.23yesterday | Free (OSS) | |||
| 3 |
AI SDKVercel |
68 | 47.2M | up 3.9% | up 38.4% | 28.1K+30/day | 7.0.1772d ago | Free (OSS) | |||
| 4 |
Claude Agent SDKAnthropic |
64 | 29.3M | up 5.9% | up 37.6% | 8,588+9/day | 0.2.185yesterday | Free (OSS) | |||
| 5 |
MastraMastra |
63 | 3.7M | up 14.9% | up 49.9% | 29.6K+23/day | 1.84.02d ago | Free (OSS) | |||
| 7 |
Deep AgentsLangChain |
59 | 3.1M | up 4.9% | up 51.3% | 31.4K+29/day | 0.2.112d ago | Free (OSS) | |||
Head to head: OpenAI Agents SDK vs LangGraph · OpenAI Agents SDK vs CrewAI · OpenAI Agents SDK vs Claude Agent SDK · OpenAI Agents SDK vs LangChain · OpenAI Agents SDK vs Strands Agents · OpenAI Agents SDK vs AI SDK
Tools used with OpenAI Agents SDK
What 521 public GitHub projects that depend on OpenAI Agents SDK use with it, from their dependency files.
- TypeScript44.3%
- Zod41.7%
- OpenAI Python Library36.1%
- python-dotenv35.1%
- React26.7%
- OpenAI26.3%
- Pydantic25.9%
- dotenv23.4%
- ESLint22.6%
- Tailwind CSS21.9%
Used far more often here than in AI-built projects overall: what sets OpenAI Agents SDK projects apart.
- Griffe8.8% · 92.0×
- jiter9.8% · 21.9×
- distro9.6% · 17.1×
- attrs8.6% · 12.9×
- sse-starlette8.4% · 11.2×
- Colorama9.2% · 10.3×
- charset-normalizer10.0% · 9.3×
- Streamlit9.2% · 8.5×
Ratings from people who use OpenAI Agents SDK
No ratings yet. Used OpenAI Agents SDK? Rate it and say what it is good and bad at.
OpenAI Agents SDK news
-
OpenAI Agents SDK 0.25.0 released
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…
What changed: recent OpenAI Agents SDK releases
7 stable releases in the last 90 days · Monthly summary · Full changelog
- Update custom error formatters. RunConfig.tool_error_formatter can receive kind="tool_exception" and an optional error. Handle the new kind or return None to retain the default message.
- Plan upgrades around saved runs. New RunState snapshots use schema 1.21. Finish affected older same-name agent graphs on their original SDK. Keep the agent code and original hook ordering unchanged.
- Recover completed work more reliably. Deferred approval history, completed tool outputs, aliases, and compaction state survive supported recovery paths. Automatic compaction waits for approvals.
- Harden local execution and display. macOS sandbox commands deny Launch Services requests. Sandbox tools recover from invalid model arguments.
- Honor tracing choices through resume and cleanup. Per-run tracing opt-out applies inside caller traces, and approved resumed tools attach to the resumed agent span.
- Use richer integration examples and metadata. MCP tools expose optional mcp_annotations as discovery hints.
Earlier releases
- restore release tests and refresh required readiness check (730deb4)
- The clean candidate contains current main a575a6e637feb9aea1b591237b007dd4991ddfba plus only six release-owned metadata files.
- Relative to v0.23.0, SDK runtime source changes only its version string. API snapshot content, dependencies, Python support and persisted schemas are unchanged.
- Risk: 🟢 LOW with the previously reviewed migration paths. Users upgrading from 0.22.3 receive the 0.23.0 behavior changes as well as this patch.
- Evidence: PyPI has neither 0.23.0 nor 0.23.1. The 0.23.0 release assessment in #5226 covers strict tools, approval restoration, encrypted history, resource limits, voice defaults and provider…
- Files: CHANGELOG.md, src/agents/version.py; unchanged 0.23.0 runtime contracts assessed in #5226.
- mcp: add configurable MCP listing page limits (9a21ab1)
- sandbox: add opt-in Docker removal protection (ae5803f)
- sandbox: allow configuring memory consolidation turns (daa1bcb)
- sessions: add an opt-in encrypted history scan budget (a2fdb94)
- avoid awaiting cleanup during coroutine closure (719c4e7)
- ci: update and group CodeQL actions together (f76153c)
- fix(core): align conditional approvals with validated tool arguments
- fix(core): deliver tool-not-found output on server-managed resume
- fix(sandbox): keep command paths POSIX on a Windows host
- fix(sessions): handle concurrent async SQLite startup
- fix(sessions): do not forward session limit as Conversations page size
- fix(tracing): do not cache a missing OPENAI_API_KEY
- feat: support current image generation tool options
- fix(sandbox): prevent UnixLocal file API symlink races
- fix(sessions): reset compaction response chain after pop
- docs: document v0.22.1 behavior updates
- release: 0.22.2
OpenAI Agents SDK prices over time
OpenAI Agents SDK popularity and usage data
OpenAI Agents SDK was downloaded 7.2M times from npm and PyPI in the week ending Nov 17, 2026, up 4.8% on the week before and up 38.9% over the last 30 days compared with the 30 before. The GitHub repository has 30.8K stars, 665 of them added in the last 30 days. The latest stable release is 0.25.0, published Nov 18, 2026; there was 1 stable release in the past 30 days. It was mentioned in 5 Hacker News posts and comments over the last 30 days.
Download the raw daily series: openai-agents-sdk.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Hacker News mentions | Nov 18, 2026 | Nov 19, 06:26 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
OpenAI Agents SDK FAQ
How much does OpenAI Agents SDK cost?
OpenAI Agents SDK is open source and free to use; you pay only for the models and infrastructure it runs on.
Is OpenAI Agents SDK open source?
Yes. OpenAI Agents SDK is open source, released under the MIT license.
How popular is OpenAI Agents SDK?
OpenAI Agents SDK was downloaded 7.2M times from npm and PyPI in the week ending Nov 17, 2026, up 4.8% on the week before and up 38.9% over the last 30 days compared with the 30 before. The GitHub repository has 30.8K stars, 665 of them added in the last 30 days. The latest stable release is 0.25.0, published Nov 18, 2026; there was 1 stable release in the past 30 days.
What is the latest version of OpenAI Agents SDK?
The latest stable release we track is 0.25.0, published on Nov 18, 2026.
What are the alternatives to OpenAI Agents SDK?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.
For the makers of OpenAI Agents SDK badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/openai-agents-sdk/)
[](https://agentgid.com/agents/openai-agents-sdk/)
[](https://agentgid.com/agents/openai-agents-sdk/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
npm: @openai/agents. PyPI: openai-agents. GitHub: openai/openai-agents-python. See data sources for how each one is collected.