SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI developer platforms

3,637 results · Page 21 of 102

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

RAGEN

AI developer platforms

RAGEN is an open-source reinforcement learning framework for training reasoning LLM agents, based on the StarPO algorithm and supporting multi-turn trajectory-level reinforcement learning. It provides 10 built-in environments (such as Sokoban, FrozenLake, WebShop, DeepCoder, SearchQA, etc.) and a Gym-compatible interface, making it easy to add custom environments. The RAGEN-2 version further introduces SNR-Adaptive Filtering, a lightweight trajectory filtering method based on reward variance, as well as reasoning collapse diagnostics (detecting template collapse through conditional entropy and mutual information proxy metrics), helping to understand and fix hidden failure modes in agent reinforcement learning (such as Echo Trap and reasoning collapse). The framework supports two optimization methods, PPO and GRPO, and includes tools such as a diagnostics dashboard and training metrics guide.

Read more

RAGEN

AI developer platforms

RAGEN is a reinforcement learning framework for training reasoning LLM agents, supporting multi-turn reinforcement learning based on the StarPO algorithm. It provides trajectory-level and turn-level training, 10 built-in environments, and a Gym-compatible interface, making it easy to add custom environments. RAGEN-2 further introduces SNR adaptive filtering based on reward variance and reasoning collapse diagnostic metrics to mitigate issues such as template collapse and improve training stability.

Read more