Agentic Research Directory

Agentic Research Directory

AI tools, agent skills, frameworks and workflows for academic research.

Browse reviewed resources, from everyday literature review, writing and data analysis to autonomous research. Inclusion is not a claim of proven benefit.

4 resources match the current filters (39 in the catalogue).

Workflow level (L1–L4) describes how AI is used, not evidence quality. Higher is not better evidence. Source level and outcome verification are separate labels. Read the method.

Active filters Clear all

  1. Framework Stanford Open Virtual Assistant Lab 2024

    STORM: a framework for source-grounded pre-writing and knowledge curation

    A modular LLM framework gathers information through retrieval and multi-perspective question asking, then produces outlines and cited drafts. It is a research pre-writing starting point, not a validated end-to-end academic writing service.

    Workflow level n/a Source Mixed sources Outcome Not empirically evaluated here

    3 sources Source-checked 2026-10-15 Computer scienceMultidisciplinary Knowledge synthesisLiterature researchScientific writing

  2. Framework PyWhy / Microsoft Research ALICE

    EconML: causal machine-learning methods for research

    A Python framework that applies machine learning to individualized causal responses using observational or experimental data.

    Workflow level n/a Source Project-documented Outcome Not empirically evaluated here

    2 sources Source-checked 2026-10-15 Business & managementEconomicsSocial science Data analysisResearch coding

  3. Framework LangChain

    LangGraph

    LangGraph is an orchestration runtime for stateful agents that can combine deterministic and LLM-driven steps.

    Workflow level n/a Source Project-documented Outcome Not empirically evaluated here

    1 source Source-checked 2026-10-15 Multidisciplinary Research codingWorkflow orchestration

  4. Framework SciSciGPT authors

    SciSciGPT

    SciSciGPT is an open-source prototype AI collaborator for science-of-science research described through empirical and analytical case studies.

    Workflow level n/a Source Peer-reviewed source Outcome Not empirically evaluated here

    1 source Source-checked 2026-10-15 MultidisciplinarySocial science Data analysisLiterature researchResearch codingWorkflow orchestration