Tag
DocJev is a free, open-source Python tool for classifying and splitting complex document packets, supporting PDF, DOCX, and PPTX with optional OCR.
Hugging Face's huggingface_hub library includes a hidden module that fingerprints AI coding agents via environment variables and sends telemetry data on API calls, raising privacy concerns discovered during a network audit.
A controlled benchmark compares CadQuery and OpenSCAD for AI agents to generate functional 3D-printable parts, revealing similar capability but differences in failure modes and tool-specific advantages.
The DSPy 3.4 release candidate is announced, moving away from litellm to improve import speed and reduce dependencies. Community members like Drew Breunig have praised the improvements.
DeepSeek has open-sourced new code repositories, including libraries and tools, to facilitate the deployment of V4.1 Flash and subsequent open-source models.
A Python and TypeScript library for downloading LLM catalogs and building pipelines to filter and select models based on criteria like price, latency, and benchmarks.
The author introduces embedflow, a method to migrate between embedding models without reindexing, saving significant time and resources. It's an open-source tool available on GitHub for easy integration into workflows.
We built an open-source retrospective reader for Claude Code to analyze agent behavior, using real execution history to inform runtime governance.
dpyr is a new Python library that replicates R's dplyr data manipulation verbs, offering method chains with Polars or DuckDB backends, IDE autocompletion, and semantics verified against dplyr.
The article explains that web agents are blocked due to inconsistent browser fingerprinting rather than the model or headless setup, and introduces pydoll, a Python library using Chrome DevTools Protocol for undetected automation.
IBM launches Docling, an open-source Python library designed to convert documents into structured data.
This paper introduces EARL, a Python library for generating counterfactual explanations in reinforcement learning to improve transparency and user trust in self-adaptive systems.
The article announces the release of bu-2-0-mini-preview, a cheaper AI model available in the Browser Use library, with input and output costs reduced from previous versions.
This paper introduces ConceptFlow, a scikit-learn-compatible Python library for Formal Concept Analysis that generates nested line diagrams, applied to analyze voting patterns and musical characteristics of Eurovision Song Contest winners.
UniFace is an open-source Python library that provides a unified API for face detection, recognition, tracking, gaze estimation, and other tasks, designed for computer vision projects.
This article introduces oncothresh, a Python library and web dashboard for evaluating oncology AI models at specific clinical decision thresholds, providing metrics like sensitivity, specificity, and decision-curve analysis to fill gaps in existing benchmarks.
City2Graph is a new Python library that converts geospatial data into heterogeneous graphs for spatial analysis and Graph Neural Networks, with a peer-reviewed paper published in Computers, Environment and Urban Systems. It supports morphological, transport, mobility, and proximity graph construction, integrating with PyTorch Geometric and other graph tools.
HyperSAE is an open-source Python library that uses hyperbolic geometry to organize LLM learned concepts into browsable tree structures, improving on flat feature lists. It captures 99.8% of Gemma-2-2B's features and includes interactive demos.
Introduces tvscreener, a Python library that can directly fetch TradingView stock screener data, supports multiple markets and 13,000+ technical indicators, returns Pandas DataFrame, and is convenient for quantitative strategy use.
A simple Python library retrieves data from TradingView Screener, featuring a visual code generator for 13,000+ fields and Model Context Protocol (MCP) support for AI assistants.