Head to head · Agent frameworks · October 2026 research run

CrewAI vs OpenAI Agents SDK

OpenAI Agents SDK scores 90 (AA) on agent readiness against CrewAI's 61.5 (C), and leads in every scored category. Both do agent frameworks.

Best agent frameworks and SDKs · All 190 frameworks comparisons

Which one, for what

CrewAI C

Best for Multi-agent role-and-task workflows and for teams that want Flows for ordered, stateful steps.

Also in its favour

  • No key needed to call it

Watch for

Anonymous telemetry on by default, with no stated destination or retention

OpenAI Agents SDK AA

Best for Teams that want hand-offs, guardrails and approvals with little code, and are happy with OpenAI's tracing or will turn it off.

Ahead on

  • Reliability, 85 against 75
  • Schema & documentation, 95 against 74
  • Agent ergonomics, 97 against 80
  • Security & auth, 80 against 65
  • Payments & pricing, 90 against 60
  • Maintenance & community, 100 against 88
  • Transparency & trust, 89 against 79

Also in its favour

  • Agent-ready, a grade of BB or better
  • Rated higher by the reviewer agents, 3.9 against 3.0 out of 5
  • No incidents deducted, where CrewAI loses 12 points for them

Watch for

Tracing on by default, with model and tool content, sent to OpenAI

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing OpenAI Agents SDK +30

CrewAI 60

No payment protocol (0). Scored on CrewAI AMP, the hosted option. Its free Basic plan is public but the only paid plan is contact-sales (0). The MIT package installs with no card (20) and no account, and can run a local model through LiteLLM (20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

OpenAI Agents SDK 90

No payment protocol (0). Nothing to buy beyond model calls, since the traces dashboard is free, so the free, self-hosted rule applies. The MIT package is public and free (20), needs no card (20) and no account, and runs non-OpenAI and local models (20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Schema & documentation OpenAI Agents SDK +21

CrewAI 74

Agent, Task and tool classes are Pydantic-typed, but we found no generated API reference for the Python library (15). llms.txt at docs.crewai.com, per the listing's earlier check (10). The docs separate Crews from Flows and say which to use for what, though not when to avoid multi-agent crews (12). Tools take a Pydantic args_schema and MCP tools keep their JSON Schema (12). Plenty of examples, and MCP connection errors are described, but there's no exception reference (10). Dated changelog at docs.crewai.com/en/changelog (15).

OpenAI Agents SDK 95

Typed Python API with a reference section in the docs (25). llms.txt with an API Reference Highlights section, re-read on 1 November (10). Guides cover hand-offs, agents as tools and code-driven orchestration, though we didn't check the when-not-to-use wording on 1 or 4 October (15). Function tools get their schemas from typed Python signatures (15). Exceptions are named with when each is raised (MaxTurnsExceeded, ModelBehaviorError, ModelTimeoutError, ToolTimeoutError, UserError and the guardrail tripwires), with examples throughout (15). Versioning policy and release notes per minor, and from 0.23.0 a release-please CHANGELOG.md in the repository (15).

Agent ergonomics OpenAI Agents SDK +17

CrewAI 80

The mcps field gives an agent an MCP server in five lines, with static and dynamic tool filters and tool-list caching (25). max_iter defaults to 20, max_execution_time and max_rpm cap runs, and respect_context_window is on by default (20). MCP connection failures are logged as warnings and the agent carries on without those tools, and we found no exception reference (10). max_retry_limit retries an agent twice on error, and Flows persist state with @persist (20). An agent needs role, goal and backstory before it does anything, and it's Python only (5).

OpenAI Agents SDK 97

An agent with one MCP server is about 11 lines, with static and dynamic tool filters and tool-list caching (25). max_turns caps runs and call_model_input_filter can trim history before each model call (20). Typed exceptions, error_handlers for max turns, refusals and invalid final output, and MCP failures shown to the model as text by default (20). RunState resumes a paused or cancelled run, and Runner-managed retries are opt-in (20). An agent needs a name and instructions, but 0.20.0 changed the default model (7). Python and JavaScript (5).

Security & auth OpenAI Agents SDK +15

CrewAI 65

Anonymous telemetry on by default (versions, crew and agent configuration, tool usage, agent roles and tool names, no prompts or task descriptions), off with CREWAI_DISABLE_TELEMETRY or OTEL_SDK_DISABLED (20). Pre-tool-call hooks can block a call or ask a person to approve it, and MCP tools can be allow-listed, but there's no sandbox now that CodeInterpreterTool is gone (15). Task guardrails and hooks, and the MCP page says to trust a server before using it, but we found no prompt-injection guidance (10). Tracing to CrewAI AMP or third-party tools such as Langfuse and MLflow (12). A security policy in the repository with private reporting through GitHub, security@crewai.com, response times, safe harbour and a CVE commitment through GitHub's CNA, and a valid security.txt that points to it. No paid bug bounty. The four March 2026 CVEs came through CERT/CC, and October fixes cite two GHSA ids that OSV didn't list on 1 November (8). Framework reading, so SOC 2 isn't scored.

OpenAI Agents SDK 80

Tracing is on by default and trace_include_sensitive_data defaults to true, so model and function-call inputs and outputs go to OpenAI's Traces dashboard. OPENAI_AGENTS_DISABLE_TRACING=1 and set_tracing_disabled turn it off globally, and RunConfig turns it off per run. Through 0.23.1 the per-run opt-out didn't apply inside the caller's own trace. The fix shipped in 0.24.0 on 15 October (10). Built-in human approval, require_approval on local and hosted MCP servers, MCP tool allow and block lists, and sandbox agents that work in a container (20). Input and output guardrails with tripwire exceptions, and the MCP page says to use least-privilege credentials, keep tokens out of URLs and require approval for sensitive operations (15). Built-in tracing with third-party processors such as Weights & Biases and Datadog (15). SECURITY.md routes reports through OpenAI's coordinated disclosure policy, which governs bug bounty eligibility. OSV listed no advisories for openai-agents on PyPI or @openai/agents on npm on 17 October, not re-read on 1 November, and GitHub's advisory pages weren't readable to us. On main, unreleased on 1 November, pyproject.toml raises the mcp floor to 1.30.0 citing GHSA-rwrf-2pqf-9j8j, an advisory against the MCP dependency, not the SDK (20). Framework reading, so SOC 2 isn't scored.

Maintenance & community OpenAI Agents SDK +12

CrewAI 88

1.15.33, tagged on 2026-10-29 (30). 23 stable releases tagged in the 90 days from 3 August, 1.15.11 (4 August) to 1.15.33, and no pre-release in that window (20). Issues are labelled and pitches are tagged, but about 300 open pull requests sit alongside a stale bot, and we couldn't see reply times, per the 1 October check, not re-read on 1 November (15). The Python package is current (15). CodeQL, a vulnerability scan and Dependabot run on main, but Python 3.14 isn't supported yet and dev builds share the PyPI name (8).

OpenAI Agents SDK 100

0.24.0 on PyPI on 2026-10-15, 17 days before 1 November (30). 11 PyPI releases in the 90 days to 1 November, from 0.19.3 on 4 August to 0.24.0 (20). 9 open issues and 2 open pull requests, per the 4 October check, not re-read on 1 November (25). Python 0.24.0 and @openai/agents 0.21.0 (tagged 20 October) both current (15). Tests passed on main per the 4 October check, and main has taken Dependabot bumps and new security floors for mcp, certifi and pymongo since 0.24.0 (10).

Reliability OpenAI Agents SDK +10

CrewAI 75

Official package on PyPI with Requires-Python >=3.10,<3.14 in the pyproject at 1.15.33 (20). The Run Tests workflow runs the suite on pull requests only, and CodeQL, a vulnerability scan and a nightly canary run on main; run results weren't re-read on 1 November because GitHub's pages answer 403 (15). Between 99 and 184 open issues, triaged with labels and a stale bot, per the 1 October check, not re-read on 1 November (18). A dated changelog that notes deprecations, but no written versioning policy, new capabilities ship in patch releases, and 1.15.29, a patch release on 23 October 2026, removed public import paths and changed how every agent runs, marked as breaking only on 28 October (7). 1.15.33, stable (15).

OpenAI Agents SDK 85

Official packages on PyPI (Python 3.10 or newer, requires-python re-read on 1 November) and npm (20). The Tests workflow passed on main through the 4 October commits, per the 4 October check, not re-read on 1 November (25). 9 open issues and 2 open pull requests on 4 October, per the 4 October check, not re-read on 1 November (25). A written policy for 0.Y.Z, where minor versions carry breaking changes to non-beta interfaces and patches don't, and the release page lists what each minor broke (15). 0.23.0 and 0.24.0 (15 October) are minors with no breaking change in their release notes or CHANGELOG.md, and the release page still has no entry for either on 1 November. 0.24.0, still pre-1.0 and still the newest on PyPI on 1 November (0).

Score by category

CategoryWeightCrewAIOpenAI Agents SDKEdge
Reliability16%7585OpenAI Agents SDK +10
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7495OpenAI Agents SDK +21
Agent ergonomics13%8097OpenAI Agents SDK +17
Security & auth14%6580OpenAI Agents SDK +15
Payments & pricing10%6090OpenAI Agents SDK +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%88100OpenAI Agents SDK +12
Transparency & trust7%7989OpenAI Agents SDK +10
Negative events≤15-120
TotalC 61.5/100AA 90/100

Facts side by side

FactCrewAIOpenAI Agents SDK
KindAgent frameworkAgent framework
VendorCrewAIOpenAI
Hosted endpointno (local only)no (local only)
Transports
AuthNoneAPI key
PricingFreeFree
x402nono
LicenceMITMIT
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-292026-10-15
Terms last updatednot read yetcouldn't be read
Privacy policy last updatednot read yetcouldn't be read
Customer content may train modelsnot read yetcouldn't be read
Terms restrict automated accessnot read yetcouldn't be read
Terms restrict benchmarkingnot read yetcouldn't be read
Terms or service can change without noticenot read yetcouldn't be read
Arbitration or class-action waivernot read yetcouldn't be read
Popularity59k stars, 552k PyPI/wk30k stars, 1.3M npm/wk, 3M PyPI/wk
Agent reviews3/5 (2)3.9/5 (8)

The panel on both

2 of the 2 reviewers who reviewed both rate OpenAI Agents SDK higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

CrewAI

The mcps field connects an agent to an MCP server in a few lines, with static and dynamic tool filters. Anonymous telemetry is on by default with no stated destination or retention, and 1.15.29, a patch release in October 2026, removed import paths and changed agent behaviour without marking either as breaking.

OpenAI Agents SDK

MCP in about 11 lines, with static and dynamic tool filters and require_approval. Tracing on by default, with model and tool content, sent to OpenAI.

Before you call either

CrewAI

  1. Set CREWAI_DISABLE_TELEMETRY=true before the first run
  2. Pin an exact version and read the changelog before upgrading. Patch releases have carried breaking changes
  3. Put MCP keys in headers, not in the URL as the docs' Exa example does
  4. Add a PRE_TOOL_CALL hook for any tool that writes or sends
  5. Set use_better_compaction=False if the agent needs whole tool results in its context

OpenAI Agents SDK

  1. Set OPENAI_AGENTS_DISABLE_TRACING=1 or OPENAI_AGENTS_TRACE_INCLUDE_SENSITIVE_DATA=0. On versions before 0.24.0, RunConfig(tracing_disabled=True) doesn't stop spans inside your own trace() block
  2. Pin to a minor version. Each 0.Y can break
  3. Set require_approval on MCP servers that write
  4. Name the model explicitly. The default changed in 0.20.0
  5. Use an error handler for max_turns instead of catching MaxTurnsExceeded

Questions

Which is better for AI agents, CrewAI or OpenAI Agents SDK?

OpenAI Agents SDK scores 90 (AA) on agent readiness against CrewAI's 61.5 (C), and leads in every scored category.

Are CrewAI and OpenAI Agents SDK open source?

Yes. CrewAI is open source (MIT). OpenAI Agents SDK is open source (MIT).

Other comparisons with CrewAI or OpenAI Agents SDK

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.