“code generation”

Run and troubleshoot repository code generation after detecting the generator contract.

Generate production-quality code from requirements.

Write new code (functions, endpoints, components) as small, incremental, reviewable diffs rather than large rewrites.

Generate QR codes from text or URLs.

Maps API JSON to Vue/React components with Zod schemas and live UI previews

Compliance verdicts for AI-generated code.

Kilo Code: AI Coding Agent, Copilot, and Autocomplete

kilocode

Open Source AI coding agent that generates code from natural language, automates tasks, and runs terminal commands.

Luno Code: AI Coding Agent, Chat & Remote Control

Luno

AI coding agent for VS Code: generates code from natural language, runs terminal commands, and edits multi-file projects behind an approval gate you control.

git-ai

git-ai

Keep track of code generated by AI.

Subagent "catalog-generator" from davila7/claude-code-templates: Regenerates the component catalog (docs/components.json) by running the Python script.

AGENTS.md from redis/ioredis: 116 lines covering Project Overview, Common Commands, Generated Code, Architecture and more.

CLAUDE.md from nrwl/nx: 245 lines covering Documentation Contributions, GitHub Issue Response Mode, Avoid making changes to generated files, Code Comments and…

Release truth engine for AI-generated code.

Open-source multi-agent coding system from the HKU Data Intelligence Lab, written in Python

Google's AI coding assistant for IDEs and the terminal, sold as Standard and Enterprise editions through Google Cloud.

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code…

Open-source infrastructure that runs AI-generated code in isolated cloud sandboxes.

Secure, elastic infrastructure that runs AI-generated code in sandboxes created in under 90 milliseconds.

Code sandboxes built from Docker-image snapshots for running agent and model-generated code, with Python and TypeScript SDKs.

Rust library for LLM applications with agents, tool calling, streaming and 20+ model providers, plus a terminal coding agent.

TypeScript library that lets agents call MCP and UTCP tools by running model-written code in a sandbox.

TypeScript toolkit for AI apps and agents with a unified provider API, streaming, UI hooks and a wrapper for running established agent harnesses.

Apache-2.0 drag-and-drop studio for AG2 multi-agent apps that generates self-contained Python code.

Game-style visual builder for AI agents, with WeChat channel binding, a ReAct code assistant and an orchestrator service.

Visual builder that turns a text description into AI workflows and backend APIs, with full code access when needed

Microsoft AI service that detects harmful text and image content and screens user input for prompt attacks.

Continuously refreshed coding benchmark built from new contest problems to limit training-data contamination.