SuperAPI AI Directory
Partner with us中文AI newsFavorites

All AI tools

35,721 results · Page 148 of 993

Prototyper

AI design

Prototyper is an AI prototyping tool for the visual design field, enabling AI agents (such as Claude Code, Codex, Cursor, or the built-in agent) to build runnable apps, wireframes, and slide presentations on a shared canvas. Every element on the canvas is real, and design is code: move a shape, and the code updates with it; edit the code, and the canvas changes in sync. Designers, engineers, and agents on a team collaborate on the same canvas, generating content based on real design rules and avoiding telltale AI-generated artifacts. It supports connecting to existing toolchains such as GitHub, Drive, Linear, Notion, Figma, MCP servers, and CI, so you can start using it as soon as you open a workspace. It offers a free start, and paid plans unlock code export, collaboration, and advanced features.

Read more

pythia

AI developer platforms

Pythia is an open-source large language model suite and interpretability research project released by EleutherAI, aimed at studying how knowledge develops and evolves in autoregressive Transformers during training, combining interpretability analysis and scaling laws. The suite contains 8 model sizes, all trained on the same data in the same order, and provides 154 training checkpoints. All models, data, and code are public, supporting reproducible research. The project also hosts code and documentation for several related papers, such as "Emergent and Predictable Memorization in Large Language Models" and "PolyPythias." The models are hosted on Hugging Face and can be loaded via transformers. It is suitable for research on interpretability, learning dynamics, ethics, and transparency, and requires a certain level of technical ability.

Read more

qasphere-mcp

AI developer platforms

qasphere-mcp is an MCP server for the QA Sphere test management system (TMS), archived and no longer maintained. It enables large language models to interact directly with QA Sphere test cases, supporting discovery, summarization, and discussion of specific test cases in MCP-compatible AI-enhanced IDEs. According to the repository description, QA Sphere now directly provides a hosted MCP server, so there is no need to deploy this standalone package locally; the hosted server is always in sync with the QA Sphere API, exposes all available tools according to the user's role, and requires no local installation of anything. The recommended configuration method is to go to Settings ⚙️ → MCP Server in QA Sphere, select the assistant and access level, add an API key, and complete the setup following the on-page instructions. Using the local standalone server requires a QA Sphere account (with API access), an API key (Settings ⚙️ → API Keys → Add API Key), and your company's QA Sphere URL. The repository also provides configuration guidance for clients such as Claude and Cursor, as well as a general configuration template. The project is licensed under the MIT License.

Read more

qgis_mcp

AI developer platforms

QGISMCP is an integration project based on the Model Context Protocol (MCP), used to connect QGIS Desktop with Claude AI, enabling Claude to directly control and operate QGIS through natural language prompts. The project is built on BlenderMCP and uses sockets for two-way communication. Its main capabilities include: creating, loading, and saving QGIS projects; adding or removing vector/raster layers; executing processing algorithms from the Processing Toolbox; and running arbitrary Python code from Claude. The system consists of two parts: a QGIS plugin that establishes a socket server within QGIS, and a Python server that implements MCP and connects to the plugin. Before use, you need to install QGIS 3.X (only tested on 3.22), Python 3.10+, and the uv package manager, and follow the instructions to copy the plugin to the QGIS plugin directory, enable the plugin, and configure Claude Desktop's claude_desktop_config.json. After installation and startup, you can see the hammer icon and the tool list in Claude (such as ping, load_project, add_vector_layer, execute_processing, execute_code, etc.). Note: the ability to execute arbitrary Python code is very powerful and must be used with caution.

Read more