Open Source Code Generation Tools
Code generation uses software to produce source code or structured output from inputs such as templates, schemas, specifications, or natural-language instructions. It can reduce repetitive work, help maintain consistency across large codebases, and translate logic between languages or formats. Depending on the approach, generated output may be deterministic or produced with machine-learning models, and it may require review and testing before use.
Open source tools in this area include template engines, schema-based generators, language transpilers, and AI-assisted coding systems that create or modify files. When choosing one, consider its license, maintenance activity, supported languages, output quality, security practices, and fit with your existing workflow. Check whether it handles your project’s scale and requirements, and how easily you can inspect, customize, and test its output. These tools can help individual developers, teams, researchers, and organizations automate software tasks.
15 repositories · updated October 10, 2026

awesome-ai-coding-sandboxes: Compare Agent Code Sandboxes
A curated, security-focused directory of sandboxes for running AI coding agents' code. Compare isolation boundaries, network egress controls, secrets handling, hosting options, and workspace state to shortlist tools for further evaluation.
NewHealth 36/100

adl-cli: Scaffold A2A Agent Servers from YAML
adl-cli turns YAML Agent Definition Language files into project scaffolding for A2A servers. It is aimed at developers who want consistent agent projects across Go, Rust, or TypeScript, with optional enterprise, development, and deployment setup.
ActiveHealth 78/100

agent-factory: Generate Executable AI Agent Workflows
Agent Factory turns natural-language task descriptions into executable Python agent workflows, using MCP tools and the any-agent library. It is aimed at developers who want to create, evaluate, and run agents without hand-coding every workflow.
QuietHealth 31/100

evalplus: Rigorously Evaluate LLM-Generated Code
EvalPlus evaluates code generated by language models with expanded correctness tests for HumanEval and MBPP, plus efficiency checks through EvalPerf. It is for researchers and developers comparing models or validating generated code more rigorously.
InactiveHealth 39/100

gpt-pilot: Build Apps with an AI Developer Assistant
GPT Pilot is a Python tool that works with a developer to plan, code, review, and debug applications step by step. The repository is no longer maintained and includes a security notice about a removed credential-stealing payload.
QuietHealth 39/100

py2many: Transpile Python to Multiple Programming Languages
py2many translates Python into languages including Rust, C++, Go, and Julia, with type inference to help bridge Python code to statically typed targets. It suits developers prototyping in Python who want to explore or build for other language ecosystems.
ActiveHealth 57/100

fern: Generate API SDKs and Documentation
Fern turns API definitions into SDKs and developer documentation through a command-line workflow. It suits teams that want to publish client libraries and API references from OpenAPI and other supported specifications.
ActiveHealth 71/100

Qwen3-Coder: Generate Code and Power Coding Agents
Qwen3-Coder is Qwen’s family of code-focused language models for code generation, repository-scale understanding, and agentic development tasks. It offers open-weight checkpoints in several sizes, with context lengths up to 256K tokens.
QuietHealth 34/100

Paper2Code: Generate Code Repositories from ML Papers
Paper2Code is a research project that uses specialized LLM agents to turn machine-learning papers into code repositories. It suits researchers and developers exploring paper reproduction, with setup options for OpenAI APIs or vLLM.
QuietHealth 19/100

kilocode: Use AI Coding Agents Across IDEs and CLI
Kilo Code is an AI coding agent for VS Code, JetBrains IDEs, and the command line. It helps developers generate and review code, run tools, and choose among many AI models, with modes for planning, debugging, and codebase questions.
ActiveHealth 84/100

Ditto: Generate Flask Apps from Natural Language
Ditto is an experimental coding agent that turns a plain-language app description into a multi-file Flask application. It suits developers exploring LLM-assisted scaffolding, but the project is a quick exploration rather than a maintained production tool.
InactiveHealth 23/100

gpt-engineer: Generate and Improve Code from Natural Language
gpt-engineer is a Python CLI for turning natural-language specifications into code and iterating on existing projects with AI. It suits developers experimenting with code-generation agents who want a hackable local workflow.
ArchivedHealth 38/100