community-automations/open-deep-research

Research & Intel

PublicClaude subagent

Open Deep Research

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
ClaudeClaude
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

    • Read

      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.

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.