Coding Agent

An agentic skills framework and software development methodology that provides reusable skill modules and engineered workflows for AI coding agents.

agentcodingtools +2

· Automatic workflow triggers - Agent enters brainstorming, spec design, and planning before writing code
· Subagent-driven development - Dispatches isolated subagents per task with two-stage review (spec + quality)
· Test-driven development - Enforces RED-GREEN-REFACTOR cycle; deletes code written before tests

Everything Claude Code

246.4k · JavaScript

The agent harness performance optimization system with skills, instincts, memory, security and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

codingagentjavascript +2

· Cross-harness compatibility - Works with Codex, Claude Code, Cursor, OpenCode, Gemini, Zed, GitHub Copilot, and more
· Skills and instincts system - 63 agents, 251 skills, and 79 legacy command shims as reusable behavior modules
· Memory persistence - Hooks automatically save and load context across sessions for continuous memory

Hermes Agent

240.1k · Python

agent-frameworkautonomous-agentllm +1

An autonomous AI agent framework from NousResearch that supports multiple LLM backends and grows with user needs.

· Self-improving learning loop - Auto-creates skills from experience, self-improves during use, cross-session recall
· Multi-platform messaging gateway - Single process supports Telegram, Discord, Slack, WhatsApp, Signal, and CLI
· Six terminal backends - Local, Docker, SSH, Singularity, Modal, and Daytona with serverless hibernation

OpenCode

203.3k · TypeScript

OpenCode is an open-source terminal coding agent that supports multiple LLM providers, offering AI-powered code generation and editing in the terminal.

codingcliagent +2

· Terminal TUI interface - Interactive terminal-based coding UI with multiline editing and streaming output
· Dual agent mode - Built-in build (full-access dev) and plan (read-only analysis) agents, switch with Tab
· Multi-LLM provider - Supports Anthropic, OpenAI, Google, and more with flexible configuration

Anthropic Agent Skills

173.3k · Python

Official Anthropic repository for Agent Skills, providing ready-to-use Claude agent skill examples and templates.

agentcodingclaude +3

· Dynamic skill loading — Claude loads skill folders on demand at runtime to improve performance on specialized tasks
· SKILL.md specification — Each skill is structured with YAML frontmatter and Markdown instructions for reusability
· Document capabilities — Built-in skills for creating and editing DOCX, PDF, PPTX, and XLSX documents

Claude Code

143.8k · Python

coding-agentcliterminal +2

Claude Code is an agentic coding tool by Anthropic that lives in your terminal, understands your codebase, and helps you code faster through natural language commands.

· Terminal-native experience — Runs directly in your terminal with full codebase context and structure understanding
· Natural language coding — Execute coding, refactoring, and debugging tasks through natural language commands
· Git workflow integration — Handles branching, commits, PR creation, and other Git operations

Spec Kit

133.1k · Python

spec-drivencopilotworkflow +3

GitHub's official open-source Spec-Driven Development toolkit that flips traditional software development — specifications become executable artifacts that directly generate working implementations, integrating with Copilot, Claude Code, Cursor, and other AI coding agents.

· Spec-Driven Development — specifications become executable artifacts that directly generate implementations
· Specify CLI — initialize projects and establish principles with a single command
· Multi-agent integrations — supports GitHub Copilot, Claude Code, Cursor, and other AI coding agents

CC Switch

130.7k · Rust

A cross-platform desktop All-in-One assistant tool for managing Claude Code, Codex, OpenCode, OpenClaw and Gemini CLI agents in one place.

codingagentrust +2

· Multi-agent unified management - manage Claude Code, Codex, Gemini CLI, OpenCode and more in one interface
· Built with Tauri 2 - cross-platform desktop app using Rust + WebKit with low resource usage
· API proxy switching - quickly switch between API endpoints and keys for different AI coding tools

Ponytail

121.6k · JavaScript

agent-skillscode-qualityYAGNI +2

Skill pack that makes your AI agent write minimal code like a lazy senior dev, cutting code by 54% and cost by 20%.

· Minimalist code philosophy - guides agents to prefer native APIs over dependencies
· Measurable results - 54% less code on average, up to 94% on real projects
· Safety guards - retains all safety checks without sacrificing quality for brevity

Codex CLI

121.0k · Rust

Codex CLI is OpenAI's open-source coding-agent command-line tool for code understanding, refactoring, generation, and terminal collaboration in developer workflows.

codingcliopenai +1

· Locally-running coding agent - interact with code directly in terminal for understanding, refactoring, and generation
· ChatGPT account integration - sign in with Plus/Pro/Business/Enterprise plans to use Codex
· Multi-platform installation - curl script, npm, Homebrew, and pre-built binary packages available

design-systemcoding-agentui-generation +1

Awesome DESIGN.md

113.6k · Unknown

Normal A

Awesome DESIGN.md is a collection of DESIGN.md files inspired by popular brand design systems. Drop one into your project and let coding agents generate a matching UI, providing design system references for AI coding agents.

· 72+ brand DESIGN.md files - complete design system docs for Claude, Vercel, Linear, Notion and more
· AI agent-readable format - plain Markdown, no Figma or special tools needed, LLMs parse directly
· Design tokens and patterns - includes colors, typography, spacing, component rules with real design depth

Gemini CLI

106.8k · TypeScript

Gemini CLI is a terminal-based AI agent tool from Google that supports code generation, file operations, and multi-turn conversations with a free usage tier.

codingcliagent +2

· Gemini 3 model access - 1M token context window with improved reasoning capabilities
· Built-in tool suite - Google Search grounding, file operations, shell commands, and web fetching
· MCP protocol extensibility - connect custom tools and services via Model Context Protocol

caveman

102.6k · Go

caveman is a bare-bones Claude Code TUI client, dependency-light and built for blazing-fast terminal coding.

claude-codetuicli +2

· Bare-bones TUI — No webview, no Electron, pure terminal experience that boots in an instant
· Native Claude Code integration — talks to Anthropic's Claude Code with multi-turn context preserved
· Minimal dependencies — only standard library, tiny footprint and low runtime overhead

Pi

101.0k · TypeScript

Pi is a full-stack AI agent toolkit featuring a coding agent CLI, unified LLM API, TUI and Web UI libraries, Slack bot, and vLLM inference pods.

coding-agentclillm +2

· Unified multi-provider LLM API — pi-ai package provides unified interface for OpenAI, Anthropic, Google, and other LLM providers
· Interactive coding agent CLI — pi-coding-agent provides command-line interactive coding agent with tool calling and state management
· Agent runtime — pi-agent-core provides agent runtime with tool calling and state management for multi-step task execution

research-agentautomated-researchllm-training +1

AutoResearch

95.1k · Python

Stale B

AI research automation agent by Andrej Karpathy that automatically runs nanochat training research experiments on a single GPU.

· Autonomous experiment loop - AI agent modifies training code, runs 5-min experiments, evaluates results, and keeps or discards changes
· Single-file agent editing - Agent only modifies train.py (model, optimizer, training loop) while humans edit program.md instructions
· Fixed time budget - Each experiment runs exactly 5 minutes wall clock, making val_bpb comparable across architectural changes

Open Design

93.6k · Unknown

open-design is an AI co-design platform for designers and developers, unifying Figma, drawing and code workflows into agent tasks.

designfigmaai +2

· AI design agent — natural-language prompts generate Figma components, pages and interactions
· Bi-directional Figma sync — every AI edit is written back to the source Figma file in real time
· Component-library aware — auto-detects the project's existing design system to keep style consistent

Claude Mem

93.0k · JavaScript

A Claude Code plugin that automatically captures coding session context, compresses it with AI, and injects relevant context back into future sessions for persistent memory.

codingmemoryagent +2

· Cross-session persistent memory - Automatically captures tool observations and generates semantic summaries, injecting relevant context into new sessions
· Progressive disclosure - Layered memory retrieval with token cost visibility for precise control over injected context volume
· Skill-based search - Query project history via mem-search skill with semantic project context retrieval

Agent Skills

91.7k · JavaScript

agent-skillsengineeringcoding-agent +1

Agent Skills is a curated collection of production-grade engineering skills for AI coding agents, maintained by Addy Osmani, providing battle-tested best practices and operational conventions.

· 23 engineering skills — Covers full dev lifecycle: spec definition, planning, building, testing, review, simplification, and shipping
· 7 slash commands — /spec, /plan, /build, /test, /review, /code-simplify, /ship for different dev phases
· Multi-tool compatibility — Supports Claude Code, Cursor, Gemini CLI, Windsurf, OpenCode, GitHub Copilot, and more

Zed

89.7k · Rust

High-performance multi-cursor editor with built-in AI and real-time collab.

editorairust +1

· Extreme perf — Written in Rust, 100ms cold start
· GPU-rendered — Smooth on high-DPI displays
· Built-in AI — Inline completion via Claude / OpenAI

Taste-Skill

83.7k · JavaScript

agent-skillscode-qualitywriting-style +2

Skill that gives your AI good taste, stopping agents from generating boring, generic slop content.

· Anti-AI-slop - prevents agents from generating boilerplate, generic content
· Taste guidance - trains agents to write distinctive, concise, direct content
· Cross-agent - loadable as a skill in Claude Code, Cursor and more

Screenshot to Code

77.2k · Python

screenshot-to-codemultimodalcode-generation +2

Turn screenshots, mockups, and Figma designs into clean code using AI models. Supports HTML/Tailwind, React, Vue, and other frontend frameworks.

· Multi-format input - converts screenshots, UI mockups, Figma designs and screen recordings into runnable code
· Multi-stack output - generates code for HTML+Tailwind, React+Tailwind, Vue+Tailwind, Bootstrap, Ionic and more
· Multi-model AI integration - built-in Gemini, GPT-5 series, Claude Opus models with side-by-side comparison

Learn Claude Code

75.9k · Python

A nano claude code-like agent harness built from scratch, demonstrating how to build AI coding assistants from zero to one.

codingagenttypescript +2

· Agent Harness architecture teaching - Systematic coverage of Tools + Knowledge + Observation + Action + Permissions five-layer architecture
· Build Claude Code from scratch - Implement a complete AI coding assistant in Bash, covering file ops, shell execution, and context management
· Harness engineering methodology - Deep exploration of the core philosophy: agency comes from training, harness comes from engineering

AI Agents for Beginners

73.8k · Jupyter Notebook

12 Lessons to Get Started Building AI Agents by Microsoft. Hands-on curriculum covering core agent concepts, tool use, and multi-agent collaboration.

agentframeworkpython +1

· 12 structured lessons - Covers AI agent fundamentals, tool use, and multi-agent collaboration in a progressive curriculum
· Microsoft Agent Framework - Hands-on code samples built on Azure AI Foundry Agent Service V2
· Multi-language support - Auto-translated via GitHub Action with 50+ language versions available

GPT Academic

71.3k · Python

Stale B

Multi-functional interface for GPT/GLM LLMs with optimized academic paper reading, polishing and writing. Supports multi-model parallel, plugin extensions and local deployment.

pythonllmchatbot +2

· Multi-model parallel - simultaneous support for GPT-3.5/4, ChatGLM, Qwen, DeepSeek, Spark and other mainstream LLMs
· Academic paper toolkit - one-click Arxiv paper translation/polishing, PDF full-text translation, LaTeX proofreading, Google Scholar assistance
· Plugin architecture - modular function plugin system with hot-reload and custom plugin extensibility