l0ng-ai
Featured
tty7
tty7 is a fast, GPU-accelerated terminal workbench with persistent sessions, built-in input tools, SSH support, and coding agent awareness.
academic-literature-mining-skill
A Rust-based literature mining system that verifies papers through scholarly metadata, indexes PDF pages as text and images using NVIDIA Nemotron, and stores retrievable evidence in Qdrant.
Stars
80
7-day growth
No data
Forks
3
Open issues
1
License
Apache-2.0
Last updated
2026-07-23
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It combines rigorous verification (retractions, persistent identifiers, citation completeness) with multimodal page indexing (text+image), per-paper isolation, and a deliberate lawful approach to paywalled content, making it a trustworthy foundation for research agents.
Who it is for
- Academic researchers and students conducting literature reviews
- Librarians and information specialists managing institutional access
- AI/ML engineers building research assistant agents
- Systematic reviewers needing reproducible search and audit trails
Use cases
- Discovering and verifying papers for a specific research question
- Building a citation-complete, auditable corpus for a systematic review
- Querying PDF pages by meaning while preserving visual layout (tables, charts)
- Managing and exporting a personal library with full provenance tracking
Strengths
- Every search result is independently resolved against Crossref, OpenAlex, arXiv, and optional Semantic Scholar before entering the corpus
- PDF pages are indexed as both native text and complete rendered images, preserving layout and enabling image-based retrieval for scanned pages
- Each paper receives an isolated Docker Compose project with private Qdrant service, SQLite database, and scoped vector IDs, preventing cross-corpus contamination
- Paywalled PDFs are handled through an opt-in, lawful user-assisted workflow (library-linked Chrome or manual file drop) rather than scraping
Considerations
- Pre-1.0 research tool; users must review corpus audits and field-specific quality before publication
- Requires multiple API keys (NVIDIA Build, OpenAlex, optional Elsevier) and Docker or Rust toolchain, adding setup complexity
- No built-in OCR; scanned pages without a native text layer are image-only, and extracted text is not a citation substitute
README quick start
Quick start
Description
Citation-complete agent-assisted scholarly literature mining in Rust with NVIDIA Nemotron and Qdrant
Related repositories
Similar projects matched by category, topics, and programming language.
steelbrain
Featured
reims-vgpu
reims-vgpu is an experimental virtual GPU for macOS guests that uses QEMU to decode the guest's GPU command stream and execute it through Metal or Vulkan, leveraging the built-in AppleParavirtGPU driver without requiring custom kexts.
m-novotny
Featured
memguard-rs
A Rust library that provides secure memory handling primitives including zeroization on drop, memory locking, constant-time comparison, and compile-time guarded regions, with zero dependencies and no_std support.