Back to directory

GPT Researcher

An autonomous research agent that searches the web and local documents to produce detailed, cited reports on a given topic, using planner and execution agents with any LLM provider.

GPT Researcher

GPT Researcher is an open deep-research agent for web and local research on a given task. It produces detailed, factual research reports with citations, and offers customization options for building domain-specific research agents.

Its architecture separates planner and execution agents: a planner generates research questions that together form an objective view of the task, a crawler agent gathers information for each question, and a publisher aggregates the summarized, source-tracked findings into a final report of more than 2,000 words drawing on more than 20 sources.

It can also be installed as a Claude Skill so Claude can use its research capabilities directly inside a conversation. It is written in Python and licensed Apache-2.0.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.