Some questions need more than one search; they need a system that decides what to do next based on what it just found. Open Deep Research routes itself between search, fetch, and analysis.
sonnet1 weekSearXNGFirecrawlOpenAILangGraph
Claude
68ROI
73Scale
$2.4k86Saved
ROI for
README.md
Why this subagent
Some questions need more than one search; they need a system that decides what to do next based on what it just found. Open Deep Research routes itself between search, fetch, and analysis.
It picks the right tool for each step, keeps going until the question is covered, and tracks every source along the way. You get a structured, cited answer plus the full trail of how it got there, so the work is auditable, not a black box.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Run each tool, read the output, and choose the next step based on what came back.
pending
Keep gathering until the question is covered, tracking sources the whole way.
pending
Assemble a structured, cited answer and the trail of tools and sources used.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Autonomously route between search, fetch, and analysis tools to answer the question; return the answer plus the ordered tool-and-source trail behind it.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.