Directory
Published directory entries matching your search.
autoai is an open-source Python framework for automatic artificial intelligence focused on regression and classification tasks over numerical data. It automates model search, hyper-parameter tuning, and generates high-quality Jupyter Notebook code for resulting models.
Drop-in AsyncOpenAI replacement that transparently batches requests via the Batch API for cheaper LLM inference.
Awesome AutoDL is a curated list of automated deep learning resources and an in-depth analysis, subtitled that neural architecture search is not the end. It collects papers, libraries and benchmarks covering neural architecture search and hyper-parameter optimization.
BambooAI is an LLM-driven data analyst tool that operates in a persistent Python kernel. It is available as a web app with Docker-isolated execution, supports user-provided model keys, and is compatible with open weights models via provider or local deployment.
A Towards Data Science article by Hui Wen Goh evaluating popular hallucination detectors, including G-eval, Ragas and the Trustworthy Language Model, across four public RAG datasets. Using AUROC and precision/recall, it reports how well the methods automatically flag incorrect LLM responses in retrieval-augmented generation systems.
bitnet.cpp is the official inference framework for 1-bit LLMs such as BitNet b1.58. It provides optimized kernels for inference of 1.58-bit models on CPU and GPU, with NPU support stated as coming next. The repository includes documentation and setup scripts, and the project is released under the MIT license.
BigScience Large Open-science Open-access Multilingual Language Model.
Model interpretability and understanding library for PyTorch.
The caret package provides a set of functions in R intended to streamline creating predictive models. Its tools cover data splitting, pre-processing, feature selection, model tuning using resampling and variable importance estimation, and it offers a uniform interface and standardized common tasks.
Interactive Hugging Face app that shares a machine-learning model, framework, demonstration or technical resource.
ch.at is a lightweight language model chat service accessible through HTTP, SSH, DNS, and an OpenAI-compatible API, plus a public agent board with posts, replies, feeds and search. It requires no JavaScript or tracking, and bots are welcome. State is held in RAM only, so a restart loses all data.
ChatGLM2-6B is the second-generation version of the open-source bilingual (Chinese-English) chat model ChatGLM-6B.
Repository of machine-checkable security models for Clawdbot, written primarily in TLA+ and checked with TLC. It functions as a security regression suite in which green models should pass and deliberately buggy red models should fail with a counterexample trace. Some checks are conformance-style, validating that the formal model matches Clawdbot's implementation constants.
Open-source Python library for data-centric AI that helps clean data and labels by automatically detecting issues in machine learning datasets. It uses existing models to estimate dataset problems that can be fixed to train better models. It runs on Python 3.10+ and works with any model across classification, regression, segmentation and object detection tasks.
CLIP Interrogator 2 is a Hugging Face Space that analyzes uploaded images using a CLIP model. Users select a processing mode (best, classic, or fast) and the tool returns a text prompt describing the image to support recreation of similar artwork.
A lightweight tool designed to run frontier mixture of experts (MoE) models on existing user-owned hardware. It is built with pure C programming language, has zero external dependencies, and streams model experts directly from disk, described as a tiny engine capable of running immense models.
An open-source project that provides tools to debug, evaluate, and monitor large language model (LLM) applications, retrieval-augmented generation (RAG) systems, and agentic workflows, with features including comprehensive tracing, automated evaluations, and production-ready dashboards.
A Botpress-published guide that explains large language model (LLM) agents, including their definition, core features, common types, and improvement techniques, and notes that LLM agents are AI systems for natural language tasks such as customer support and data analysis.
CoreWeave is an AI cloud platform with integrated technology and teams built for complex AI workloads. It offers Forge, described as tools for running and improving AI systems with any cloud, model or framework, and infrastructure for demanding workloads. Direct-to-Expert provides AI engineering support from CoreWeave engineers in existing channels. Forge pricing lists Free, Pro starting at $60 per month billed monthly, and Enterprise custom plans.
Cortex is cloud infrastructure for machine learning at scale, used to deploy, manage and scale machine learning models in production. It supports realtime, async and batch serverless workloads, along with automated cluster management including cluster autoscaling and spot instances with on-demand backups. Environments, provisioning and CI/CD and observability integrations are also listed. A notice states the project is joining Databricks.
Credyt is real-time monetization infrastructure for AI. It is intended to let builders observe spend per API call, model and customer, enforce budget limits before usage is authorized, and bill customers across usage-based, subscription, hybrid, credit and token pricing models. The team cites backgrounds at Visa, Checkout.com, TrueLayer and SumUp.
DagsHub is an AI platform for managing the machine learning lifecycle, covering dataset curation and annotation, experiment tracking, and model management. It supports unstructured and multimodal data such as text, images, audio, video, and documents. The platform is built on open source tools and formats. DagsHub states it does not currently provide compute resources and relies on the user's own infrastructure.
Enjoy unlimited API calls with Serverless AI Workers/LLMs for just $25 per month. No rate or concurrency limits.
An agentic LLM for autonomous data science that performs data preparation, analysis, modeling, visualization, and report generation without human intervention. It supports open-ended research on structured, semi-structured, and unstructured data sources, and the model, code, training data, and demo are open-sourced.
