SuperAPI AI Directory
Partner中文AI newsFavorites

All AI tools

35,738 results · Page 547 of 993

Aura screenshot

AI finance

Aura is a comprehensive identity theft and online fraud protection service for the whole family, covering identity, credit, financial, and device security, with support for Windows, Mac, iOS, Android, and major browsers. Key capabilities include credit monitoring and credit lock, identity theft protection, suspicious transaction alerts, privacy assistant, spam call blocking, VPN, password manager, antivirus, parental controls, and in-game cyberbullying alerts. The company says plans start at $10 per month, and it offers $1 million identity theft insurance, a 60-day money-back guarantee, and 24/7 U.S.-based support, and uses AI to detect phishing, scam texts, and robocalls.

Read more

Aural

AI coding

Aural is an AI interview platform that supports conducting text chat, voice, and video interviews at scale, and provides automatic insights, transcripts, and analytics. Through structured adaptive interviews, it helps users focus on key insights. The platform supports designing custom interviews, AI adjusting follow-up questions in real time, automatically generating summaries, and exporting structured data (XLSX/PDF). Aural offers a free tier with no credit card required, and is fully open source (MIT License), can be cloud-hosted or self-deployed, and comes with a REST API and OpenAPI specification for developers and AI agents to integrate.

Read more

Auralume AI

AI video

Auralume AI is an all-in-one AI video generation platform that can transform text prompts, images, or videos into cinematic videos. The platform has built-in models such as Seedance, Veo, Kling, and Grok, and selects and tunes them based on quality, motion, speed, and cost-effectiveness, allowing creators to use them directly without needing to research models. Its features include "create first, set up later" default parameters, video-aware guidance for motion, composition, image quality, and sound, and a unified workspace that starts from a sentence or a still image. In terms of pricing, it offers one-time purchases and annual subscriptions: the $278.40 annual plan includes 1,500 credits per month and standard response speed; the $950.40 annual plan includes 6,600 credits per month, priority response and priority email support, and includes stealth mode. Credits do not expire, payment is based on usage, and generated content in the public gallery is visible.

Read more

auto product image

AI images

Auto Product Image is an AI product image generation tool for e-commerce sellers that turns a single source product photo into product image sets suitable for platforms such as Amazon, Shopify, TikTok Shop, and Google Shopping. After the user selects a platform, image type, and style, the AI preserves the product's shape, material, color, and details based on the uploaded photo, and batch-generates main images, lifestyle scene images, feature callout images, and social ad crop images. The tool provides image slots grouped by platform, an asset library, and basic compliance checks to help sellers efficiently produce product images that are ready to publish.

Read more

Auto-claude-code-research-in-sleep

AI agents

ARIS (Auto-Research-In-Sleep) is a lightweight workflow solution for machine learning research, consisting mainly of pure Markdown skills (Skills). It does not depend on a specific framework and is not locked to any platform. Its core idea is to let an execution model advance research tasks while another independent model reviews the results, thereby forming a cross-model review loop and supporting idea discovery and experiment automation. ARIS can run in various LLM agent environments such as Claude Code, Codex CLI, Cursor, Trae, GitHub Copilot CLI, OpenClaw, and others, and can also be installed and used through the standalone ARIS-Code CLI or as a plugin. According to the project description, ARIS is a methodology rather than a platform, with the focus on the research workflow itself, so users can bring the same process to different tools. In addition to the core skills, the project also includes supporting components such as a command-line tool, plugins, a review bridge, and a monitoring widget, and provides Chinese documentation.

Read more

auto-deep-researcher-24x7

AI search

Auto Deep Researcher 24x7 is an autonomous AI agent for deep learning experiments that can automatically run experiments 24/7 while you sleep. It uses a Leader-Worker architecture with a constant-size two-layer memory, and significantly reduces overhead through zero-cost monitoring (no LLM calls during training), with the official claim of about $0.08 per 24-hour cycle. The work loop is THINK → EXECUTE → REFLECT: read the project brief, analyze historical results, plan the next experiment, modify code/config and do a dry run before launching training on the GPU, monitor the training process at zero LLM cost, parse results, compare with the baseline and decide the next step, then repeat. It supports local/SSH/Slurm execution backends, and supports access to Chinese LLM APIs such as DeepSeek, Qwen (dashscope), Kimi (moonshot), and GLM (zhipu) through provider presets. It has a built-in experiment ledger, stagnation signals, research logs, violation scanning and phase gates, anti-burn rate limiting, code understanding and literature retrieval tools, and supports exporting progress to Obsidian or local text.

Read more

Auto-Slides

AI office

Auto-Slides is an automatic academic presentation generation system proposed by institutions such as the AGI Lab at Westlake University (the official implementation of ICME 2026). Based on large language models and principles of cognitive science, it automatically converts academic research paper PDFs into well-structured, teaching-oriented presentation slides. The system adopts a multi-agent collaboration framework, including PDF parsing, presentation planning, content verification, and automatic repair, supports multimodal output such as images, tables, and code highlighting, and provides natural language interactive customization, multiple Beamer themes, bilingual Chinese-English support, and optional speech script generation. The project is open source under the MIT License and requires a locally installed LaTeX environment and configuration of an OpenAI API key.

Read more

AutoAct

AI agents

AutoAct is an automatic agent learning framework that does not require large-scale annotated data and synthetic trajectories from closed-source models. Users only need to provide limited data and a tool library, and AutoAct can automatically synthesize planning trajectories and, based on the target task information, automatically differentiate into a collaborative group of sub-agents (such as planning, tool, reflection, and other roles) to complete the task. The framework aims to reduce the reliance of language agent systems on expensive, non-reproducible data and to alleviate the challenge of a single model taking on multiple functions. Experiments show that AutoAct can achieve performance superior to or close to strong baselines on different large language models. The official website is a project showcase page, and specific ways to obtain the relevant training data, models, and code are not yet provided.

Read more