AI coding & agents · Daily GitHub chart, Tue, Nov 17
AI coding & agents repositories pooled from every language chart and re-ranked by stars gained. As of Tue, Nov 17, 9 PM GMT+9.
- 1
obra/superpowers
Agentic skills framework and software development methodology
Superpowers is a software development methodology for coding agents built on composable skills that trigger automatically. Instead of jumping straight into code, it guides agents through brainstorming, design approval, implementation planning, and subagent-driven execution.
+1,905that day
- 2
ag-ui-protocol/ag-ui
Open event-based protocol connecting AI agents to frontend apps
An open, lightweight, event-based protocol that standardizes how AI agents connect to user-facing applications. It replaces custom wiring with a bi-directional event stream so any client can render agent outputs regardless of the underlying agent framework.
+1,444that day
- 3
stablyai/orca
Parallel coding agent orchestrator app
Orca lets you run Claude Code, Codex, and other CLI coding agents in parallel, each in its own isolated worktree. It brings chat, terminal, diff review, a browser, and a CLI together across desktop, mobile, and remote runtimes.
+1,052that day
- 4
elementalsouls/Claude-BugHunter
Claude Code skill bundle for bug hunting and red-team work
A self-contained skill bundle for Claude Code designed for bug bounty hunting and external red-team engagements. It combines disclosed vulnerability report patterns with enterprise identity and infrastructure attack matrices.
+1,007that day
- 5
NVIDIA/SkillEvaluator
Multi-tier evaluation framework for AI agent skills and plugins
SkillEvaluator is a multi-tier framework that checks AI agent skills and plugins for quality, security, overlap, and compatibility, and measures how they affect task results. It supports keyless static quality checks as well as sandboxed live agent evaluations.
+969that day
- 6
mattpocock/skills
Composable engineering skills for AI coding agents
A collection of small, composable skills for coding agents such as Claude Code, Codex, GitHub Copilot, and Gemini CLI. It provides repeatable workflows for aligning requirements, TDD, debugging, and reviewing codebase architecture.
+793that day
- 7
DietrichGebert/ponytail
Minimal-code skill for AI coding agents
A skill and ruleset that guides AI coding agents to reuse existing code and write only what a task requires without cutting validation, security, or tests. It works across hosts such as Claude Code, Codex, and Cursor.
+785that day
- 8
tradermonty/claude-trading-skills
Claude Skills trading workflow toolkit for individual investors
A trading workflow toolkit for Claude Web and Claude Code that structures market review, risk management, trade planning, and journaling. Rather than automating orders or providing buy/sell signals, it focuses on supporting a trader's decision process.
+771that day
- 9
alibaba/open-code-review
Hybrid deterministic and LLM code review CLI
An AI-powered code review CLI tool that reads Git diffs or full files to generate line-level review comments. It combines deterministic file selection and rule matching with an LLM agent for dynamic context retrieval.
+764that day
- 10
affaan-m/ECC
Performance optimization system for AI coding agents
ECC adds planning, testing, code review, and memory workflows to coding agents like Claude Code, Codex, and Cursor. It bundles 72 agents, 327 skills, hooks, and security scanning into a single installable system.
+718that day
- 11
pbakaus/impeccable
Design vocabulary and slop detector for coding agents
Impeccable provides a skill set and CLI that help coding agents steer UI designs, run usability and technical reviews, and catch common AI-generated design patterns. It works across tools such as Claude Code, Cursor, Codex CLI, and GitHub Copilot.
+693that day
- 12
backnotprop/plannotator
Local review and annotation workspace for AI coding agents
Plannotator is a local browser-based review workspace where you can annotate plans, documents, HTML artifacts, and code diffs from AI coding agents and send feedback directly back to the agent. It connects through plugins, hooks, and MCP so agents can keep working while you review.
+691that day
- 13
milind-soni/OpenMausBot
Open-source desktop chat app for local AI agent teams
OpenMausBot is an open-source, local-first desktop app that lets you run a roster of AI bots powered by your existing Claude, Codex, and Grok CLIs inside a messaging interface. Each bot has its own model, a cloud or local virtual machine for computer use, and connected apps, with inline approval cards before executing sensitive actions.
+662that day
- 14
tashfeenahmed/freellmapi
Unified OpenAI-compatible router for free LLM APIs
Aggregates 87 free LLM providers and 1,313 free model endpoints behind a single OpenAI-compatible `/v1` API. It also supports Anthropic, Gemini, Ollama, and custom OpenAI-compatible endpoints.
+649that day
- 15
Graphify-Labs/graphify
Knowledge graph builder for codebases and docs
Graphify turns a codebase along with its docs, SQL schemas, configs, and PDFs into a queryable knowledge graph. It runs as a `/graphify` skill in AI coding assistants using local deterministic AST parsing without a vector store.
+615that day
- 16
Tencent/LoopForge
Self-hosted workflow platform for coding agents
LoopForge is a self-hosted workspace by Tencent for shipping software with coding agents. It lets teams work through chat with Main Bot or run repeatable SOPs that combine agents, scripts, and human approval gates.
+590that day
- 17
ChromeDevTools/chrome-devtools-mcp
Chrome DevTools MCP server for coding agents
An MCP server and CLI tool that lets coding agents such as Antigravity, Claude, Cursor, and Copilot control and inspect a live Chrome browser. It exposes Chrome DevTools capabilities for browser automation, debugging, and performance analysis.
+562that day
- 18
kajisho5/ffmpeg-skill
Local FFmpeg video editing skill for coding agents
An Agent Skill and MCP server that lets coding agents like Claude Code, Cursor, and Codex edit video with local FFmpeg and verify the output. It ships 42 structured tools backed by a machine-readable contract and runs locally without cloud services or API keys.
+367that day
- 19
google-labs-code/stitch-skills
Agent skills and plugins library for Google Stitch
A collection of agent skills and plugins designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard for compatibility with coding agents such as Codex, Antigravity, Gemini CLI, Claude Code, Cursor, and OpenCode.
+350that day
- 20
nightly-labs/openbot
Local-first desktop workspace for persistent AI agents
OpenBot is a local-first desktop app for running persistent AI agents such as Codex, Claude, Grok, Gemini, and Cursor in dedicated workspaces. It provides message queues, file transfers, an embedded browser, and agent-to-agent collaboration in one place.
+343that day
- 21
JuliusBrussee/caveman
Token-saving skill and proxy for coding agents
Caveman is a skill and proxy for AI coding agents that cuts token usage by shortening agent replies and compressing the data they read. It keeps code, commands, and file paths verbatim while trimming unnecessary prose.
+318that day
- 22
farion1231/cc-switch
Desktop manager for AI coding assistants and API providers
A cross-platform desktop application for managing Claude Code, Codex, Gemini CLI, OpenCode, and other AI coding tools. It lets you switch API providers in one click and manage MCP, Skills, and Prompts without hand-editing JSON, TOML, or YAML config files.
+312that day
- 23
msitarzewski/agency-agents
Specialized AI agent collection for coding tools
A collection of specialized AI agent personas covering roles such as frontend developer, backend architect, and code reviewer. Each agent file defines an identity, workflow, technical deliverables with code examples, and success metrics.
+275that day
- 24
citrolabs/ego-lite
Browser for parallel AI agent web automation
ego lite is a browser where AI agents run web automation in isolated Spaces while you keep browsing your own tabs. Through the ego-browser skill, agents like Claude Code and Codex share your local logins and cookies without taking over your browser.
+253that day
- 25
coreyhaines31/marketingskills
Marketing skills collection for AI coding agents
A collection of markdown-based skills that give AI coding agents specialized workflows for marketing tasks. It works with Claude Code, OpenAI Codex, Cursor, Windsurf, and other agents supporting the Agent Skills spec.
+239that day