Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

PaperSeek

Open-source literature search, citation exploration, and abstract-based reviews.

PaperSeek turns a research question into a reading list. It plans and refines queries, retrieves papers from your chosen source, expands citations where supported, and ranks relevance. Explore the results in a bilingual Web workspace, save local history, and export a reading list.

Project overview · Documentation · 中文文档 · Try online

Install

Requires Python 3.12 or newer. The release package includes the Web UI.

python -m pip install "paperseek==1.0.0b2"
paperseek serve

Open http://127.0.0.1:8765. Configure a model API and data source in the application.

Capabilities

  • Eight scholarly sources: OpenAlex, arXiv, Crossref, Semantic Scholar, PubMed, Google Scholar via Serper, PaperHub, and Web of Science Starter.
  • Query iteration, bounded candidate retrieval, optional citation expansion, and relevance ranking.
  • OpenAI Responses, OpenAI-compatible Chat Completions, and Anthropic Messages model protocols.
  • Local fusion, Embedding + Rerank, or System One preliminary ranking.
  • Search history, filters, selection, citation maps, and complete CSV/JSON exports.
  • Experimental abstract-based reviews with editable outlines, section writing, versions, and Markdown/Word/BibTeX exports.

A run begins with one selected data source. Search is bounded, not guaranteed exhaustive; reviews use available abstracts and metadata rather than automatically read full texts.

Terminal and integrations

The CLI provides serve, worker, search, doctor, migrate, and version. Configure process environment variables before a terminal search; a nearby .env is not loaded automatically.

paperseek search "How does open-source funding affect maintenance?" --source openalex --search-budget medium --output json

The local HTTP API is under /api/v1, with its schema at /openapi.json. MCP is packaged separately:

python -m pip install "paperseek-mcp==1.0.0b2"
paperseek-mcp --transport stdio

Data and upgrades

Community stores history in ~/.paperseek/paperseek.db by default, with artifacts and credential-encryption material in its data directory. Back up the complete directory consistently.

For Docker, separate workers, and 0.2 migration, see self-hosting and upgrading.

Development and license

The source distribution uses paperseek_core for research behavior, paperseek_app for use cases and ports, and paperseek_community for local adapters. Hosted consumes a fixed Community distribution. Common Vue sources are included for Hosted builds; installed Community serves the prebuilt assets.

Development guide · Report an issue · Apache-2.0 license

Metadata

Release files for paperseek 1.0.0b2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for paperseek 1.0.0b2
File Interpreter ABI Platform
paperseek-1.0.0b2-py3-none-any.whl Python 3 none any Details

Release files / paperseek-1.0.0b2-py3-none-any.whl

Download URL paperseek-1.0.0b2-py3-none-any.whl
Size 781.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1f04ac7152292cc2ce4d15383c71ce741e1cb344483bbbdd0a2edab19048e711
BLAKE2b-256 checksum
How to use checksums
18cdcc0076519ab73037c95925dc8058e27b1a87d7125c5ff53baf579c327655
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Security for paperseek 1.0.0b2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page