AI Coding Open-Source Projects

Showing 40 indexable projects from the current snapshot.

• stablyai/orca

  Orca is a desktop and mobile development environment that orchestrates CLI coding agents across parallel isolated git worktrees. Developers can run multiple agents concurrently, compare their diffs, and monitor progress remotely.

• openai/codex-plugin-cc

  A Claude Code plugin that delegates read-only code reviews, adversarial design challenges, and background tasks to Codex without leaving the current workflow. It is intended for developers who use both Claude Code and Codex and want to red…

• Nutlope/hallmark

  A design skill for coding agents that applies macrostructures, themes, and 57 slop-test gates to produce varied UI code and avoid on-distribution AI design defaults.

• obra/superpowers

  A skills framework and software development methodology that applies test-driven development and subagent-driven workflows for AI coding agents. It activates before code is written to refine designs, dispatches fresh subagents per task, an…

• affaan-m/ECC

  A system of over 260 reusable skills, rules, and hooks designed to standardize AI-assisted software development across multiple agent harnesses. It provides cross-harness automations, a security scanner for agent configurations, and an exp…

• anomalyco/opencode

  anomalyco/opencode is an open source AI coding agent providing both a full-access Build Agent for development work and a read-only Plan Agent for codebase analysis. It runs as a binary, desktop application, or Node package on macOS, Window…

• anthropics/claude-code

  Claude Code is a terminal-native agentic coding tool that uses natural language commands to execute routine tasks, explain code, and manage git workflows. It is designed for developers seeking to accelerate coding through an AI agent that…

• msitarzewski/agency-agents

  A collection of specialized, personality-driven AI agents organized into divisions such as engineering, design, and security, packaged with scripts for installation into multiple agentic coding tools.

• github/spec-kit

  A specification-driven development toolkit that makes product specifications executable to generate working software implementations. It provides slash commands, agent skills, and preset workflows for teams using AI coding assistants.

• farion1231/cc-switch

  A cross-platform desktop GUI that centralizes provider configuration, MCP server setup, and skills management across seven AI coding tools. It is built for developers who regularly switch between multiple AI tools and need a visual interfa…

• continuedev/continue

  An open-source AI coding agent available as a CLI tool, a VS Code extension, and a JetBrains plugin. The repository is currently read-only with no active maintenance, and the JetBrains plugin is deprecated.

• browser-use/browser-use

  browser-use/browser-use is a Python library and CLI that lets an AI agent operate a web browser to perform tasks described in natural language. Developers can use it for code-level browser automation and structured data extraction without…

• google-gemini/gemini-cli

  google-gemini/gemini-cli is a terminal-first AI agent that brings Gemini models into the command line for code understanding, generation, and workflow automation. It provides file operations, shell commands, web fetching, and extensibility…

• VoltAgent/awesome-design-md

  A curated collection of 73 plain-text DESIGN.md files extracted from real-world brand design systems. You drop a markdown file into your project root to give AI coding agents the structured context needed to generate visually consistent UI.

• openai/codex

  OpenAI Codex is a terminal-based coding agent that runs locally on the user's computer and integrates with ChatGPT or the OpenAI API. It requires an OpenAI account or API key to function.

• TabbyML/tabby

  A self-contained, open-source AI coding assistant designed as an on-premises alternative to GitHub Copilot. It operates without requiring a DBMS or cloud service and supports consumer-grade GPUs for local inference.

• Graphify-Labs/graphify

  Graphify converts local project directories into queryable knowledge graphs using deterministic tree-sitter AST parsing across approximately 40 programming languages without requiring LLM calls. It outputs an interactive HTML visualization…

• practical-tutorials/project-based-learning

  A curated list of programming tutorials organized by primary programming language, designed for aspiring software developers who want to learn by building applications from scratch. It functions primarily as a discovery resource for findin…

• getify/You-Dont-Know-JS

  A completed book series that explores core JavaScript mechanisms in depth, available to read online at no cost. It is intended for developers and learners who want detailed educational coverage of how the language works.

• DietrichGebert/ponytail

  Ponytail is a Node-based, locally runnable skill for AI coding assistants that applies a reuse-first decision ladder before new code is written. On skill-capable hosts, it also supports diff review and repository audits that produce a dele…

• OpenHands/OpenHands

  OpenHands is a self-hosted developer control center for starting, managing, and automating coding agents across local and remote environments. It supports running agents across multiple backends and allows developers to bring their own LLM.

• addyosmani/agent-skills

  A collection of 24 structured engineering workflow skills and 8 slash commands designed to enforce senior-level software development discipline in AI coding agents across define, plan, build, verify, review, and ship phases.

• earendil-works/pi

  A self-hosted coding agent and CLI framework that unifies multiple hosted LLM APIs (OpenAI, Anthropic, Google) into a single interface. Requires external API credentials and lacks a built-in permission system, making external sandboxing ne…

• rtk-ai/rtk

  RTK is a single Rust binary with zero dependencies that reduces LLM token consumption by 60-90% during agentic coding tasks by intercepting, filtering, grouping, truncating, and deduplicating terminal command outputs. It supports auto-rewr…

• shareAI-lab/learn-claude-code

  A 0-to-1 educational project teaching harness engineering through 20 progressive lessons, showing how to build the operational environment around an LLM step-by-step. It is designed for developers who want to understand agent capabilities…

• Leonxlnx/taste-skill

  Portable agent skills that improve AI-generated frontend code and reference images with stronger layout, typography, motion, and spacing. Users adjust output through numeric dials for design variance, motion intensity, and visual density.

• openinterpreter/openinterpreter

  A Rust-based coding agent derived from OpenAI's Codex that optimizes harness performance for low-cost models. It executes terminal commands within native OS sandboxing and runs as an Agent Client Protocol agent.

• Fission-AI/OpenSpec

  OpenSpec adds a specification layer to AI-assisted coding so teams agree on requirements before implementation. It uses slash commands to generate and manage proposals, design documents, specs, and tasks within existing projects.

• upstash/context7

  Context7 injects current, version-specific library documentation and code examples into LLM prompts, addressing hallucinated or outdated API usage. It operates as an MCP server or CLI tool integrated into coding agents, relying on a privat…

• pbakaus/impeccable

  A design language and skill collection for AI coding agents that provides shared design vocabulary, deterministic detector rules, and live browser iteration to address repetitive AI-generated frontend patterns. It runs without an LLM for d…

• aaif-goose/goose

  Goose is a general-purpose AI agent that runs natively on your machine via a desktop app, CLI, or API. It supports multiple LLM providers and MCP extensions for diverse tasks beyond code suggestions.

• Avik-Jain/100-Days-Of-ML-Code

  A 100-day educational machine learning track providing daily Markdown tutorials, Python code snippets, and visual infographics for common algorithms. The repository is designed for self-paced learning and is not intended for production dep…

• hesreallyhim/awesome-claude-code

  A hand-picked catalog of resources for Claude Code, covering skills, agents, developer tooling, and plugins. It organizes materials under topics such as security, multi-agent orchestration, and observability, though it is currently undergo…

• GokuMohandas/Made-With-ML

  A course with accompanying code that teaches developers to design, develop, deploy, and iterate on production-grade machine learning applications. It covers the combination of machine learning and software engineering practices needed to b…

• jeecgboot/JeecgBoot

  JeecgBoot is a Java-based low-code and no-code platform that uses natural language prompts to generate full-stack business systems, forms, workflows, reports, and dashboards. It includes an integrated AIGC platform with RAG knowledge base…

• HKUDS/CLI-Anything

  cli-anything generates structured CLI harnesses from software source code so that AI agents can operate them. It bridges AI agents and existing software by making applications agent-native through generated command-line interfaces.

• abhigyanpatwari/GitNexus

  GitNexus indexes Git repositories or ZIP files into a precomputed knowledge graph using Tree-sitter, exposing structural context through 17 MCP tools or a browser-based UI. It supports AI coding agents by providing dependencies, call chain…

• microsoft/Web-Dev-For-Beginners

  A 12-week, 24-lesson curriculum teaching JavaScript, CSS, and HTML fundamentals through project-based pedagogy. It includes post-lesson quizzes, offline documentation access, and multi-language translations, purposefully avoiding JavaScrip…

• aymericdamien/TensorFlow-Examples

  This repository provides concise tutorials and source code for learning TensorFlow v1 and v2, covering basic models, neural networks, data management, and hardware. It is designed for developers and educators who need clear, executable exa…

• Alishahryar1/free-claude-code

  A local proxy and Admin UI that routes Claude Code, Codex, and Pi agent traffic to free, paid, or local model providers. It enables developers to select, validate, and manage multiple providers from a single interface.