[
  {
    "id": "openai-agents-docs-1",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/agents/",
    "excerpt": "An agent is a large language model (LLM) configured with instructions, tools, and optional runtime behavior such as handoffs, guardrails, and structured outputs.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-2",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tools/",
    "excerpt": "The WebSearchTool lets an agent search the web.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-3",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tools/",
    "excerpt": "FunctionTool instances: wrap any Python function as a tool.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-4",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/handoffs/",
    "excerpt": "Handoffs allow an agent to delegate tasks to another agent. This is particularly useful in scenarios where different agents specialize in distinct areas.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-5",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/guardrails/",
    "excerpt": "Guardrails enable you to do checks and validations of user input and agent output.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-6",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/streaming/",
    "excerpt": "Streaming lets you subscribe to updates of the agent run as it proceeds. This can be useful for showing the end-user progress updates and partial responses.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-7",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/running_agents/",
    "excerpt": "You can run agents via the Runner class. You have 3 options: Runner.run(), Runner.run_sync(), Runner.run_streamed()",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-8",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/sessions/",
    "excerpt": "The Agents SDK provides built-in session memory to automatically maintain conversation history across multiple agent runs, eliminating the need to manually handle `.to_input_list()` between turns.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-9",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tracing/",
    "excerpt": "The Agents SDK includes built-in tracing, collecting a comprehensive record of events during an agent run: LLM generations, tool calls, handoffs, guardrails, and even custom events that occur.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-10",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/mcp/",
    "excerpt": "The Agents Python SDK understands multiple MCP transports. This lets you reuse existing MCP servers or build your own to expose filesystem, HTTP, or connector backed tools to an agent.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-11",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/models/",
    "excerpt": "The Agents SDK comes with out-of-the-box support for OpenAI models in two flavors",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-12",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-js/guides/human-in-the-loop/",
    "excerpt": "When a tool call requires approval, the SDK pauses the run, returns interruptions, and lets you resume later from the same RunState.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-13",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/",
    "excerpt": "Voice agents: Build voice pipelines that combine speech-to-text, an agent workflow, and text-to-speech.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-14",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/",
    "excerpt": "Sandbox agents: Run specialists inside real isolated workspaces. Sandbox agents support manifest-defined files, sandbox client selection, and resumable sandbox sessions.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-15",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-js/",
    "excerpt": "Build text, sandbox, and voice agents with a small set of primitives.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-16",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tracing/",
    "excerpt": "Using the Traces dashboard, you can debug, visualize, and monitor your workflows during development and in production.",
    "fetchedAt": "2026-09-04T00:15:26.935Z"
  },
  {
    "id": "openai-agents-docs-17",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/running_agents/",
    "excerpt": "You have 3 options: Runner.run(), Runner.run_sync(), Runner.run_streamed()",
    "fetchedAt": "2026-09-04T00:17:40.390Z"
  },
  {
    "id": "openai-agents-docs-18",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tracing/",
    "excerpt": "The Agents SDK includes built-in tracing, collecting a comprehensive record of events during an agent run: LLM generations, tool calls, handoffs, guardrails, and even custom events that occur. Using the Traces dashboard, you can debug, visualize, and monitor your workflows",
    "fetchedAt": "2026-09-04T00:17:40.390Z"
  },
  {
    "id": "openai-agents-docs-19",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/",
    "excerpt": "Function tools: Turn any Python function into a tool with automatic schema generation and Pydantic-powered validation.",
    "fetchedAt": "2026-09-04T00:17:40.390Z"
  },
  {
    "id": "openai-agents-docs-20",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-js/guides/human-in-the-loop/",
    "excerpt": "When a tool call requires approval, the SDK pauses the run, returns `interruptions`, and lets you resume later from the same `RunState`.",
    "fetchedAt": "2026-09-04T00:17:40.390Z"
  },
  {
    "id": "openai-agents-docs-21",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tools/",
    "excerpt": "OpenAI offers a few built-in tools when using the OpenAIResponsesModel... The WebSearchTool lets an agent search the web. The FileSearchTool allows retrieving information from your OpenAI Vector Stores. The CodeInterpreterTool lets the LLM execute code in a sandboxed environment.",
    "fetchedAt": "2026-09-04T00:17:40.390Z"
  },
  {
    "id": "openai-agents-docs-22",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tools/",
    "excerpt": "Agents as tools: expose an agent as a callable tool without a full handoff.",
    "fetchedAt": "2026-09-04T00:17:40.390Z"
  },
  {
    "id": "openai-agents-docs-23",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-js/",
    "excerpt": "RealtimeAgent, RealtimeSession... Automatically connects your microphone and audio output in the browser via WebRTC.",
    "fetchedAt": "2026-09-04T00:17:40.390Z"
  },
  {
    "id": "openai-agents-docs-24",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tools/",
    "excerpt": "`FunctionTool` instances: wrap any Python function as a tool.",
    "fetchedAt": "2026-09-04T00:19:42.174Z"
  },
  {
    "id": "openai-agents-docs-25",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tools/",
    "excerpt": "Use OpenAI-managed tools (web search, file search, code interpreter, hosted MCP, image generation)",
    "fetchedAt": "2026-09-04T00:19:42.174Z"
  },
  {
    "id": "openai-agents-docs-26",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/running_agents/",
    "excerpt": "You can run agents via the `Runner` class. You have 3 options: `Runner.run()`... `Runner.run_sync()`... `Runner.run_streamed()`",
    "fetchedAt": "2026-09-04T00:19:42.174Z"
  },
  {
    "id": "openai-agents-docs-27",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tracing/",
    "excerpt": "The Agents SDK includes built-in tracing, collecting a comprehensive record of events during an agent run: LLM generations, tool calls, handoffs, guardrails, and even custom events that occur. Using the [Traces dashboard], you can debug, visualize, and monitor your workflows",
    "fetchedAt": "2026-09-04T00:19:42.174Z"
  },
  {
    "id": "openai-agents-docs-28",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/models/",
    "excerpt": "if you want to consistently use a specific model for all agents that do not set a custom model, set the `OPENAI_DEFAULT_MODEL` environment variable before running your agents.",
    "fetchedAt": "2026-09-04T00:19:42.174Z"
  },
  {
    "id": "openai-agents-gh-1",
    "tier": "github",
    "url": "https://github.com/openai/openai-agents-python",
    "excerpt": "It is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs, as well as 100+ other LLMs.",
    "fetchedAt": "2026-09-04T00:19:42.174Z"
  },
  {
    "id": "openai-agents-docs-29",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/",
    "excerpt": "Agents, which are LLMs equipped with instructions and tools",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-docs-30",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/handoffs/",
    "excerpt": "Handoffs allow an agent to delegate tasks to another agent.",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-docs-31",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/tracing/",
    "excerpt": "The Agents SDK includes built-in tracing, collecting a comprehensive record of events during an agent run",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-docs-32",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/streaming/",
    "excerpt": "Streaming lets you subscribe to updates of the agent run as it proceeds.",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-docs-33",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/sessions/",
    "excerpt": "The Agents SDK provides built-in session memory to automatically maintain conversation history across multiple agent runs",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-docs-34",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/running_agents/",
    "excerpt": "Runner.run_streamed(), which runs async and returns a RunResultStreaming",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-docs-35",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/mcp/",
    "excerpt": "The Agents Python SDK understands multiple MCP transports. This lets you reuse existing MCP servers or build your own",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-docs-36",
    "tier": "claimed-docs",
    "url": "https://openai.github.io/openai-agents-python/agents/",
    "excerpt": "If the agent should run inside an isolated workspace with manifest-defined files and sandbox-native capabilities, read Sandbox agent concepts.",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-gh-2",
    "tier": "github",
    "url": "https://github.com/openai/openai-agents-python",
    "excerpt": "Voice agents: Build voice pipelines that combine speech-to-text, an agent workflow, and text-to-speech",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-gh-3",
    "tier": "github",
    "url": "https://github.com/openai/openai-agents-python",
    "excerpt": "Realtime agents: Build powerful voice agents with `gpt-realtime-2.1` and full agent features",
    "fetchedAt": "2026-09-16T00:08:43.086Z"
  },
  {
    "id": "openai-agents-comm-1",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/44353964",
    "excerpt": "OpenAI SDK is much simpler to use and understand than langchain etc. I havent deployed really complicated agents, but I have a number of simple use cases that work just fine",
    "fetchedAt": "2026-09-04T00:28:57.936Z"
  },
  {
    "id": "openai-agents-comm-2",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/44353964",
    "excerpt": "you're better off just implementing the logic yourself as it is more flexible.",
    "fetchedAt": "2026-09-04T00:28:57.936Z"
  },
  {
    "id": "openai-agents-comm-3",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/44353964",
    "excerpt": "I agree with the debugging part - we need a new approach to handle these abstractions, and a regular code-stepping or reading logs isn't enough in the case of agents.",
    "fetchedAt": "2026-09-04T00:28:57.936Z"
  },
  {
    "id": "openai-agents-comm-4",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44736713",
    "excerpt": "Comparing the Temporal-based durable version to the original OpenAI Agents SDK repo's examples, it's really not all that different - some metadata to denote workflow/activity and different function calls but otherwise quite similar.",
    "fetchedAt": "2026-09-04T00:28:57.936Z"
  },
  {
    "id": "openai-agents-probe-1",
    "tier": "probe",
    "url": "https://developers.openai.com/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://developers.openai.com/llms.txt # OpenAI Developers\n\n> Complete documentation hub for OpenAI API, Ads, Plugins, Workspace Agents, Codex, Agentic Commerc",
    "fetchedAt": "2026-09-16T00:08:44.315Z"
  },
  {
    "id": "openai-agents-probe-2",
    "tier": "probe",
    "url": "https://developers.openai.com/api/docs/guides/agents.md",
    "excerpt": "PROBE docs-md: HTTP 200 at https://developers.openai.com/api/docs/guides/agents.md # Agents\n\n> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages ar",
    "fetchedAt": "2026-09-16T00:08:44.315Z"
  },
  {
    "id": "openai-agents-probe-3",
    "tier": "probe",
    "url": "https://developers.openai.com/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://developers.openai.com/openapi.json, https://developers.openai.com/swagger.json, https://developers.openai.com/api/openapi.json, https://developers.openai.com/.well-known/openapi.json)",
    "fetchedAt": "2026-09-16T00:08:44.315Z"
  }
]