claudeers.

Fresh Commits

// most recent commits — actively being worked on

// observatory (3725)

🔓

Minimal by design, explicitly multi-lang, production-ready and battle-tested collection of configs and plugins for your Claude Code agentic development workf…

// skillsserpro69/⟨Shell⟩★ 149◷ NOASSERTION[ claude ]
🔓

Claude Code skill: distill a book or video series into one interactive single-file HTML · 书籍/视频深度蒸馏

// skillssanshengai/⟨Python⟩★ 48◷ MIT[ claude ]
🔓

Free, bidirectional Figma MCP server — turn designs into framework-aware code and write back to the canvas, for Claude Code, Cursor, and any MCP client.

// mcp-serversawdr74100/⟨TypeScript⟩★ 976◷ MIT[ claude ]
🔓

An open-source AI coding agent that lives in your terminal.

// frameworksQwenLM/⟨TypeScript⟩★ 28,288◷ Apache-2.0[ claude ]
🔓

Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/

// automationembabel/⟨Kotlin⟩★ 4,488◷ Apache-2.0[ claude ]
🔓

v3.10.1 · Try it: npx roast-my-design-system · Roasts your design system with real data: a health score, the receipts, the first fixes ranked by payoff, and…

// pluginspencilrebel/⟨JavaScript⟩★ 26◷ MIT[ claude ]
🔓

Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, root-cause debugger…

// devtoolsPythoughts-labs/⟨Python⟩★ 29◷ Apache-2.0[ claude ]
🔓

A comprehensive collection of Model Context Protocol (MCP) servers

// mcp-serversTensorBlock/⟨TypeScript⟩★ 874◷ MIT[ claude ]
🔓

A floating, screen-aware Claude Code chat for Windows - it reads your screen to answer, and runs on your own Claude subscription (no API key).

// automationshengyanlin/⟨Python⟩★ 95◷ MIT[ claude ]
🔓

Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

// uncategorizedImbad0202/⟨Python⟩★ 12,191◷ NOASSERTION[ claude ]
🔓

The memory-first self-improving agent harness built on EverOS.

// automationEverMind-AI/⟨Python⟩★ 5,209◷ Apache-2.0[ claude ]
🔓

Local-first MCP security scanner for AI-generated apps. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.

// mcp-serversSynvoya/⟨TypeScript⟩★ 47◷ MIT[ claude ]
🔓

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

// uncategorizedagentscope-ai/⟨Python⟩★ 3,548◷ Apache-2.0[ claude ]
🔓

Claude Code Desktop theme for DeepSeek Harness| 为 DeepSeek Harness 网页 GUI 打造的 Claude Code 桌面主题

// devtoolsNwflower/⟨JavaScript⟩★ 81◷ NOASSERTION[ claude ]
🔓

The best-benchmarked open-source AI memory system. And it's free.

// mcp-serversMemPalace/⟨Python⟩★ 59,417◷ MIT[ claude ]
🔓

9.9 元豆包API复刻 Claude Science

// dataPKU-YuanGroup/⟨Python⟩★ 608◷ MIT[ claude ]
🔓

GitHub's official MCP Server

// mcp-serversgithub/⟨Go⟩★ 33,348◷ MIT[ claude ]
🔓

Keep ai from adding unneeded modules, subagents, dependencies, and hashes to small tasks. 别再造史了,用于阻止ai过度工程,如在不必要的时候过度哈希,增加不要的全量测试等,基于hook和skill给ai划定边界 -for c…

// devtoolslennney/⟨JavaScript⟩★ 2,465◷ MIT[ claude ]
🔓

Automatically scan AUR packages for malware before installing (using LLM/AI)

// integrationsmanticore-projects/⟨Go⟩★ 154◷ NOASSERTION[ claude ]
🔓

Run any process, on your machine or in an AI agent's environment, as if it were a pod in your Kubernetes cluster: real env vars, DNS, network, traffic.

// devopsmetalbear-co/⟨Rust⟩★ 5,355◷ MIT[ claude ]
🔓

把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.

// uncategorizedisjiamu/⟨HTML⟩★ 3,886◷ NOASSERTION[ claude ]
🔓

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

// ragvolcengine/⟨Python⟩★ 39,212◷ AGPL-3.0[ claude ]
🔓

Claude Code and Codex skills for LinkedIn growth: write human-sounding posts, craft comments that get noticed, analyze your feed, and build a publishing cade…

// skillssergebulaev/⟨Python⟩★ 4,043◷ MIT[ claude ]
🔓

同花顺免费开源AI插件FQGate-agent(原插件名 tonghuasun-agent):为 Codex、Claude Code、DeepSeek 等 AI 工具提供本机 A 股实时行情、K 线、Level-2、资讯、账户查询与可选交易能力。

// mcp-serversfqgate/⟨HTML⟩★ 238◷ AGPL-3.0[ claude ]
🔓

Track your AI coding-agent token burn across Claude Code, Codex, OpenCode, Antigravity, and more.

// devtoolsfikrilal/⟨Rust⟩★ 29[ claude ]
🔓

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and…

// automationtoby-bridges/⟨Python⟩★ 865◷ AGPL-3.0[ claude ]
🔓

Claude Code skill for MiniMax H3 shot breakdown and character performance. Facial expression only renders when the shot has a <d> dialogue tag — measured, 42…

// otherphileiny/★ 172◷ MIT[ claude ]
🔓

Bring Claude Code, Codex, Cursor, Grok, OpenCode, Oh My Pi, and Pi into your Obsidian vault — a Claudian fork.

// mcp-serverslee259/⟨TypeScript⟩★ 15◷ MIT[ claude ]
🔓

A lightweight app for claude code cli agent organization in Rust

// devtoolsrespeak-io/⟨TypeScript⟩★ 20◷ MIT[ claude ]
🔓

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool call…

// ragwaybarrios/⟨Python⟩★ 1,608◷ Apache-2.0[ claude ]