SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI coding

2,763 results · Page 46 of 77

AgentRun

AI coding

AgentRun is a Python library for safely running Python code generated by large language models (LLMs). Built on the Docker Python SDK and RestrictedPython, it provides an API that executes isolated code in a single line. Key features include: checking code safety before execution, running in a fully isolated Docker container, configurable resource limits (CPU, memory, timeout), automatic dependency installation and uninstallation, dependency caching, automatic cleanup of generated files, and support for self-hosting via a REST API. The library has 97% test coverage, full static typing, and only two dependencies. It is suitable for scenarios that require letting LLMs execute code, such as mathematical calculations and data analysis, while preventing the execution of dangerous code.

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

aider

AI coding

Aider is an AI pair programming tool that runs in the terminal and works with large language models to write code. It supports cloud and local LLMs, can map the entire codebase to accommodate large projects, is compatible with more than 100 programming languages, and automatically commits changes with Git and generates sensible commit messages. Aider can be used in an IDE or editor, supports requesting changes through code comments, adding images and web pages as context, voice communication, and automatically running lint and tests after each change. Users can collaborate with any LLM through a web chat interface, simplifying the process of copying and pasting code context and edits.

Read more