Open sourcePython · ≈31k stars · MIT
OpenAI Agents SDK
A lightweight, production-ready multi-agent SDK with tracing.
The successor to the Swarm experiments: a primitives-based SDK (agents, handoffs, guardrails, sessions) with built-in tracing and MCP support. OpenAI's main contribution to the orchestration layer.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- User reportsVery easy start for function calling and sub-agents-as-tools; with the Responses API you don't have to store input items yourself.[1]
- User reportsOne long-time user says they are largely happy with its abstractions: handoffs, tools, guardrails and structured output.[1][2]
- DocsProvider-agnostic despite the name (100+ LLMs), with built-in tracing, sessions, sandbox agents and realtime/voice agents.[1]
- User reportsCommenters see it as simpler than heavier frameworks like Google ADK or LangChain, and its backlog is small (about 12 open issues).[1][2]
Cons
- Best for
- Python teams that want lightweight multi-agent primitives (handoffs, guardrails, tracing) with first-class OpenAI Responses and realtime support.
- Watch out for
- Production concerns like durability, scaling and approvals are on you; plan that layer early.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
Activity
- Last push
- · yesterday
- Latest release
- v0.25.0
· 3d ago - Last 90 days
- 11 releases
v1.0.0-alpha.1Agents SDK v1.0.0-alpha.1Pre-release
· yesterdayAgents SDK v1.0.0-alpha.1 This first preview from feat/simple-codex adds Codex as an opt-in model provider for the Python Agents SDK. The prebuilt openai-agents wheels (version 1.0.0a1) are available exclusively through GitHub Releases. Highlights Choose Codex per run. Import…
- · 3d ago
0.25.0 (2026-11-17) Key Changes Version 0.25.0 removes the beta Runloop sandbox provider and changes how Pydantic run contexts are checkpointed. Runloop users should preserve their workspace data before switching providers. Applications that share checkpoints across workers…
v0.24.0-alpha.8Agents SDK v0.24.0-alpha.8Pre-release
· 5d agoAgents SDK v0.24.0-alpha.8 Highlights Approve Python tool calls before they run. Review the arguments and approve or reject the call. You can remember a decision for the rest of the Session. Managed approval example Connect your own model client. The native tool loop works with…
v0.24.0-alpha.7Agents SDK v0.24.0-alpha.7Pre-release
· 13d agoAgents SDK v0.24.0-alpha.7 Highlights Use Classic workflows alongside native execution. Import the retained v0 runtime through agents.classic. This alpha also changes executor write defaults; review the upgrade actions before opening existing environments. Keep conversations in…
v0.24.0-alpha.6Agents SDK v0.24.0-alpha.6Pre-release
· 2w agoInstall the preview Use standard CPython 3.10–3.14 in a virtual environment. These wheels include the native runtime; no Rust toolchain or source build is needed. This preview is distributed through GitHub Releases, not PyPI. Run the command for your platform: Linux x86_64…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
In research (3)
- Skill Dreaming: Evolving Repository Skills through Pull Request StreamsVerdict: Incremental
Oct 26, 2026 · One of the six repositories in the cross-repository generalisation experiment.
Oct 26, 2026 · One of the seven frameworks surveyed for tool-output truncation behaviour.
- Tool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault ToleranceVerdict: Useful
Oct 23, 2026 · The OpenAI Agents SDK is one of the three agent stacks evaluated under faults.
Neighbours on the workbench
TypeScript · ≈395k stars · MIT
openclaw/openclaw
The viral open-source personal AI assistant that really does things.
Maintained by OpenClaw Foundation
v2026.11.6releasedTypeScript · ≈285k stars · MIT
deepseek-ai/deepseek-harness
Everything is a Plugin — DeepSeek's open agent harness.
Maintained by DeepSeek
dsh-v0.2.2-rc.5 prereleasedTypeScript · ≈212k stars · Sustainable Use License (fair-code; GitHub reports NOASSERTION)
n8n-io/n8n
Fair-code workflow automation platform with native AI capabilities.
Maintained by n8n-io
n8n@1.123.100releasedConnections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- openaiOrganisation
Built on · 1
- Model Context ProtocolProject
Built on it · 3
- Agency SwarmProject
- any-agentProject
- DBOSStartup
Mentioned in · 1
