OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Research Agents

Paper Agent

Paper-Agent is an open-source, self-hosted academic research workspace that uses a LangGraph multi-agent workflow to search papers, analyze literature and draft traceable reviews.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Paper Agent — OpenViST project profile in Research Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a literature project needs a staged path from multi-source paper search to analysis and an evidence-mapped review, with progress and session artifacts visible in a browser workspace.

Who it is for

  • Researchers exploring a topic or preparing a literature survey
  • Students organizing papers and drafting evidence-based reviews

Documented uses

  • Search arXiv, OpenAlex and Semantic Scholar for papers matching a research topic and constraints.
  • Screen abstracts, process selected full texts and build a local searchable collection.
  • Analyze subtopics and synthesize research themes, disagreements, gaps and trends.
  • Create an outline with evidence mapping and draft a review section by section.
Before you choose

Requirements & limits

The project is provided as a public repository to install and run locally; its documented setup requires model-provider and embedding configuration.

  • The documented search connectors cover arXiv, OpenAlex and Semantic Scholar.
  • Full-text processing and local vector retrieval are part of the workflow, alongside abstract screening.
  • The workspace uses SSE for progress and SQLite plus local files for session and artifact persistence.
  • The setup requires Python 3.12+, frontend dependencies and configured language-model and embedding providers.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the local research workspace

Install the documented dependencies, configure model access and open the Paper-Agent workspace.

Before you start

  • Python 3.12 or later
  • uv and npm
  • A configured model provider with a usable API key or environment variable
  • A default agent model and an embedding provider

Steps

  1. From the project root, run the command below, the command below, the command below and the command below.

    Documented command
    uv init
    Documented command
    uv venv --python 3.12
    Documented command
    uv sync
    Documented command
    npm run front:install

  2. Create the local model configuration from the supplied example, or use the workspace settings page after startup; configure a provider, credentials, default_agent and an embedding profile.

  3. Start the backend with the command below.

    Documented command
    uv run python main.py

  4. In another terminal, run the command below, open http://127.0.0.1:5173/, and use the model settings page to test the configured model.

    Documented command
    npm run front:dev

Expected outcome

The local browser workspace is available for creating research sessions after model configuration.

Guide limitations

  • The README also allows using an existing Python 3.12 virtual environment, followed by uv sync and npm run front:install.
  • A missing default_agent prevents the model configuration from working.
  • These are README setup instructions, not execution or compatibility test results.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
Tswoen/Paper-Agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction