SuperAPI AI Directory
Partner中文AI newsFavorites

All AI tools

35,738 results · Page 519 of 993

ai-agent-roadmap

AI agents

ai-agent-roadmap is a resource repository of AI Agent toolkits maintained on GitHub, aimed at tracking and summarizing the latest AI Agent-related tools and projects. The repository covers directions such as AI Agent frameworks, memory, tools, MCP, prompts, context engineering, code, deep research, evaluation, benchmarking, security, monitoring, tracing, and Agent reinforcement. The repository organizes its content in a directory format, making it convenient for developers to find resources by topic. Currently, the materials do not provide a specific tool list, usage tutorials, installation commands, or pricing information, and only state that it is positioned as a continuously updated toolkit collection.

Read more

ai-engineering-hub

AI coding

AI Engineering Hub is an open-source tutorial and project collection repository for AI engineering practice, maintained by patchy631. The repository provides more than 93 production-ready projects, covering topics such as LLMs, RAG, and AI agents, and is divided by difficulty into three levels: beginner (22), intermediate (48), and advanced (23). The content includes OCR applications, local chatbots, RAG workflows, multi-agent systems, model fine-tuning, production deployment, and more, suitable for developers of different levels to learn, experiment, and extend. The repository uses the MIT license and welcomes community contributions.

Read more

AI-Scientist

AI agents

AI-Scientist is an open-source system launched by SakanaAI, with the goal of achieving fully automated, open-ended scientific discovery. It enables foundation models such as large language models to conduct research independently: generating ideas, writing code, executing experiments, writing papers, and using LLMs for automated peer review. The project provides three templates, NanoGPT, 2D Diffusion, and Grokking, covering the corresponding research areas. The code is designed to run under Linux, NVIDIA GPU, CUDA, and PyTorch environments, and supports multiple models and API keys. Note: this code will execute code written by LLMs, which poses risks such as using dangerous packages, network access, and launching processes; you need to weigh these risks yourself and use containerization and restrict network access. In the paper, the cost per paper is usually less than $15 (using Claude Sonnet 3.5), and DeepSeek Coder V2 is recommended to reduce costs.

Read more

ai-toolkit

AI images

AI Toolkit (Ostris AI Toolkit) is a free and open-source diffusion model training suite for fine-tuning image and video generation models. It offers both GUI and CLI usage, supports training the latest models on consumer-grade hardware, and is described by its author as an all-in-one training solution. The tool covers a large number of image, video, and editing models, including FLUX.1, FLUX.2, Stable Diffusion XL, SD 1.5, Qwen-Image, the Wan 2.1/2.2 series of video models, and LTX-2, while also supporting network types such as LoRA and LoKr as well as training specified layers. Installation can be done through the built-in experimental AI Toolkit Manager, which automatically detects hardware, configures the PyTorch environment, and obtains local Node.js and FFmpeg, or manually by following the manual. Training tasks can be defined through YAML configuration files, support resuming from checkpoints, and can be run on cloud platforms such as RunPod and Modal.

Read more

ai-town

AI agents

AI Town is an MIT-licensed deployable starter kit for building and customizing your own virtual town. In AI Town, AI characters live, chat, and socialize. The project is inspired by the paper "Generative Agents: Interactive Simulacra of Human Behavior," and its main goal is to provide a platform with a robust foundation that is easy to extend. Its backend natively supports shared global state, transactions, and a simulation engine, making it suitable for scenarios ranging from simple projects to scalable multiplayer games. The second goal is to provide a JS/TS framework. Installation methods support cloud, local, Docker, and more. LLMs such as Ollama, OpenAI, Together.ai, and others can be configured. It includes a game engine, database, and vector search (Convex), optional authentication (Clerk), with the default chat model llama3 and embedding model mxbai-embed-large. Local inference supports Ollama and also other OpenAI-compatible APIs. Background music generation uses Replicate (MusicGen), and pixel art generation uses Replicate and Fal.ai. All interactions, background music, and rendering are powered by PixiJS.

Read more

AI-Writer

AI writing

AI-Writer is a Chinese pretrained generative model based on the RWKV model, specifically designed for writing novels, and can generate web fiction such as fantasy and romance. The project was developed by BlinkDL. The model is similar to GPT-2 but faster, and supports N/A/I card GPU acceleration. After downloading the model, users can run a Python script or web interface for text continuation. Note: the model's training data all comes from web fiction and lacks common life knowledge, so the generated text is for entertainment only. The project is outdated, and the author recommends using the newer RWKV-Runner and the online version.

Read more

AI365

AI assistants

Historical third-party summary: The complete xx025/carrot snapshot and LiLittleCat ChatGPT mirror list both contain the exact catalog URL at chat.ai365vip.com. The latter lists it as a web AI-chat entry and displays 2024-07-01 as the addition date, not a product launch date. Checked on2026-10-18. Only this historical chat-entry purpose is retained. Lists may borrow from each other and are not independent reviews. Free access, login requirements, model identity, browsing, image creation, unlimited quotas, current operation and access permission are unverified.

Read more