PaperSeek is an open-source literature search agent that leverages large language models (LLMs) to assist users in searching and analyzing scientific literature. The platform supports integration with a range of data sources, including OpenAlex, arXiv, Semantic Scholar, PubMed, Google Scholar (via Serper), Crossref, and computer science top conferences. Users can configure searches to include forward and backward citation traversal, enabling citation mapping and exploration of related works.
The tool offers several configurable features such as selection of LLM, embedding, and reranking services. 7-code, minimax-m3, nemotron-3-ultra-550b-a55b, deepseek-v4-flash, and others available for use. Embedding can be performed using local hashing with sparse cosine similarity as the default, or through experimental external models. Reranking is handled by default with Reciprocal Rank Fusion, but experimental reranker models can also be selected. Users have control over source and citation behavior, and can export search results to CSV format.
PaperSeek is designed for individual researchers and academic users who require efficient literature discovery and citation analysis. The service is accessible through a web interface and allows registered users to perform up to 20 successful searches per day using the PaperSeek Service, with failures not consuming the quota. For heavier use, users are encouraged to self-deploy the open-source project and use their own API keys. The platform supports third-party model and embedding providers, including ModelScope, OpenRouter, and Hugging Face, with usage subject to the selected provider's quota policies. No model API keys are stored on the server, and users can bring their own keys for various integrations.
PaperSeek is maintained as a personally managed open-source project, and the free daily search quota is limited, with no guarantees of service level agreement (SLA) stability. Email verification is required for access to the daily quota, and requests for higher quotas involve providing user details and intended use cases. The tool is suitable for those seeking a customizable and extensible solution for scientific literature exploration and citation mapping.
In the Frameworks & SDKs space, paperseek takes a focused approach. It focuses on enabling researchers to efficiently search and analyze scientific literature using LLM-powered tools. It is built as an open-source project for scientific researchers. paperseek is open source under the Apache-2.0 license. The product ships for the web and the command line.
paperseek first shipped in 2026. Development happens publicly on GitHub with 140 stars and 60 commits in the last 90 days. Key capabilities include literature search, LLM integration, and openAlex support.
Latest indexed changes and source events
Other apps tracked under the same category.
