Directory
Published directory entries matching your search.
This is the official project page for the ICML 2024 research paper 'Improving Factuality and Reasoning in Language Models through Multiagent Debate' by MIT and Google Brain researchers. The paper introduces a multi-round debate approach where multiple language model instances propose answers, critique each other, and debate to improve reasoning and factual accuracy while reducing hallucinations.
Prompt Engineering: From Words to Art - Saxifrage Blog creates or edits images with generative AI and text-based controls.
PromptEden monitors how brands appear in AI answers, compares competitors, and inspects cited sources. It also provides content creation with Eden and connects AI clients through the Model Context Protocol. Paid plans start at $49 per month.
promptext is a smart code context extractor developed for use with AI assistants. The open-source tool is hosted on the GitHub repository belonging to user 1broseidon, and is designed to pull relevant code context to improve the performance of AI coding assistants.
Promptfoo is an AI security testing platform that integrates into development workflows. It connects to AI apps, agents and CI/CD pipelines, generates context-aware attacks, and provides remediation guidance in pull requests. It offers red teaming, an open-source edition and integrations including GitHub Actions, GitLab CI, Jenkins and MCP.
Promptly is a no-code generative AI platform built for enterprise use. It allows users to build generative AI applications, AI agents and chatbots without coding experience, and supports features including model chaining, RAG pipeline creation, custom data integration, and multi-language translation. The platform offers pre-built templates for common use cases.
Promptly provides machine-learning models, research, training resources, or evaluation tools.
Prompy is a collection of curated GPT-5 and GPT-4o visual prompts intended for UI, branding and marketing work. It describes ready-to-use prompts meant to help designers, marketing strategists and agencies generate ideas and speed up design workflows.
PyCUDA is a software project associated with Andreas Klöckner, who teaches and conducts research in scientific computing at the University of Illinois at Urbana-Champaign. The project has a dedicated documentation site.
ReadSpeaker is a text-to-speech company that converts text to natural-sounding voice output for education and enterprise use cases. Its offerings include web accessibility tools, custom brand voice development, and voice AI for third-party products, with support for more than 90 languages. The company provides a range of products including text-to-speech APIs, SDKs, and embedded solutions, with sector-specific solutions for gaming, transportation, government, healthcare, and other industries.
A blog article about red-teaming large language models, described as a form of evaluation that elicits model vulnerabilities that might lead to undesirable behaviors. It discusses undesirable behaviors such as revealing personal information, misinformation, bias, hatefulness and toxic content, and compares red-teaming with adversarial attacks. It notes that red-teaming prompts look like regular natural language prompts.
Refinder AI boosts productivity in Slack and Google Chat by automating tasks, managing apps, and providing instant access to knowledge.
Roadmap is a Canny-powered feedback platform for the Saga product. It allows users to submit feedback to the Saga team to inform product decisions, and organizes submitted feature requests into Roadmap, Planned, In Progress, and Complete sections.
SciRuby is a project providing tools for scientific computing and data visualization in Ruby. Its releases include NMatrix, a linear algebra library with dense and sparse matrix storage and tensor support, alongside visualization and statistics gems. The project describes itself as currently alpha, and it notes its gems are tested but not battle-hardened. SciRuby and NMatrix are available under the BSD three-clause license.
screenpipe applies AI to workplace tasks, meetings, sales, marketing, or productivity.
Summingbird is a library for writing MapReduce programs that resemble native Scala or Java collection transformations and running them on distributed MapReduce platforms including Storm and Scalding. Programs can execute in batch mode, realtime mode, or a hybrid mode combining Scalding and Storm. The repository was archived by its owner on Jan 20, 2022 and is read-only.
textacy is a Python library for natural language processing tasks built on the spaCy library. It focuses on tasks before and after spaCy processing, with tokenization, part-of-speech tagging and dependency parsing delegated to that library. Features include cleaning and normalizing raw text, extracting n-grams, entities, acronyms and keyterms, similarity metrics, and training topic models.
TextBlob is a Python library for processing textual data. It offers a simple API for natural language processing tasks including part-of-speech tagging, noun phrase extraction, sentiment analysis, classification, and tokenization. The documentation lists features such as word and phrase frequencies, parsing n-grams, lemmatization, spelling correction, and WordNet integration. It builds on NLTK and pattern, and new models or languages can be added through extensions.
The Art of ChatGPT Prompting: A Guide to Crafting Clear and Effective Prompts creates or edits images with generative AI and text-based controls.
The GDELT Project monitors broadcast, print and web news from nearly every country in over 100 languages, identifying people, locations, organizations, themes, sources, emotions, counts, quotes, images and events. Its archives date back to January 1, 1979 and update every 15 minutes. Data can be downloaded as raw CSV files, visualized with the GDELT Analysis Service, or queried with Google BigQuery.
The Prompter vicc Substack uses AI for speech, voice, transcription, music, or other audio workflows.
TorchText provides models, data loaders and abstractions for language processing, powered by PyTorch. The library includes dataset iterators, basic NLP building blocks, text-processing transformations, pre-trained models and vocabulary classes. The repository was archived by its owner on Sep 10, 2025, and is now read-only; development is stopped with 0.18 the last stable release.
Upscaling refers to the ultimate-upscale-for-automatic1111 project, an upscaling extension for the AUTOMATIC1111 Stable Diffusion web UI. The public repository includes instructions, reference materials, example content, and API usage documentation for the tool, and contributions to the project are accepted from the public.
We must stop AI replicating the problems of surveillance capitalism provides machine-learning models, research, training resources, or evaluation…
