JavaScript

AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.

Local-first desktop widget for tracking token usage, costs, and limits across 28+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, and OpenClaw—with multi-device sync.

Main agent plans and reviews; cheaper sidekick edits. Devin Fusion pattern for OpenCode

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.

AKARI Video — AI video editing tool (Theia-based monorepo) · Site: akari.video · Asset library: akari.video/lab

让任何 Agent 帮你学懂 Vibe Coding 术语

DeepSeek V4 code worker MCP for Codex Desktop, powered by Claude Code

An extension of Nocturne to turn Spotify Car Thing into a hardware Claude Code HUD

Unified API for running OpenCode, Claude Code, Codex agents

Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.

A 3D sandcastle simulator that runs entirely on the GPU. No engine, no libraries, no asset files, no build step. Built in one prompt with Claude Code.

Stop your coding agent reading the wrong files. Compiler-grade TS/JS repo map — 100% precision on blast radius vs grep's 60%, measured on public repos. CLI + MCP server, fully local, no vector DB.

VisionPower: portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

Free Local AI inference without need for GPUs or heavy chunks of your CPU

NovelAI法典前端项目

Slap the slop out of your UI — AI-slop parallel-inspection pipeline skill for Claude Code

생년월일시만 넣으면 유료 사주 앱 같은 평생사주 18장 풀이 + 상담 모드. 진짜 만세력 엔진 기반. 바이브코더용 Claude Code 스킬. by 쓰레드 @be_realdeveloper

A lightweight Grok plugin for Claude Code — delegate coding and review tasks to the Grok CLI. A simple reimplementation of OpenAI's codex-plugin-cc.

Syncs terminal titles from workspaces, tabs, and agent sessions (use w/ Moshi)

Creative AI Ops Layer

A simple studio to use agent

Design enforcement system, not a code generator. Two independent layers (Taste Guardian + Blind Spot ESLint). 7-phase design pipeline. Zero runtime dependencies. Awwwards-level output.

Reliable browser automation skill for AI agents — Chrome lifecycle management & workflow guidance on top of chrome-devtools-mcp. | AI Agent 浏览器自动化 Skill —— 基于 chrome-devtools-mcp，提供 Chrome 生命周期管理与最佳实践指导。

"Done" means nothing — a menhera-style completion gate for Claude Code that blocks empty completion claims until tests actually ran green and no TODOs are left behind.

AI-powered rug pull detector — paste a contract, get the truth

Local AI Skills central library with per-project symlink enablement. One AISkills folder holds every skill source; symlink on demand into any project's .agents/skills or .claude/skills to share across Claude Code, Codex, OpenCode, and Pi.

Free, local voice dictation for Windows. Hold a key, speak, your words appear at the cursor. On-device Whisper, no cloud, no account, no telemetry.

A local-first masker that lives inside Claude Code, Cursor, Codex CLI, and 20+ AI agents. Hides API keys, passwords, secrets, and personal data — across PDF, Word, Excel, JSON, .env, and 45+ other formats — before your agent ever sees them.30 seconds to install. Nothing leaves your machine. Ever.

Claude Code skill that interviews founders, researches industries with live web search, and surfaces operational problems worth building a startup around.

Piece is a piece-aware build feedback system for AI-era coding agents.

Eigenwise's toolshed of Claude Code plugins. Includes codebase-mapper: a self-maintaining, language-agnostic codebase map that auto-loads into every Claude session.

Claude Code Skills, Agents & Plugins — UitKit

Experimental Chrome side-panel browser agent with LangGraph.js, MCP/WebMCP, local models, and semantic browser automation.

Tell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops with independent verification and growing memory.

MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in dynamic and adaptive modes.

本地网关和API管理器。

Universal multi-agent infrastructure for AI coding assistants. 26 specialist agents, 19 enforced workflow skills, and a lead orchestrator — for Claude Code, Codex CLI, Cursor, and OpenCode.

TÜRKPATENT marka/patent/tasarım araması için Claude-in-Chrome skill

OpenAI-compatible local AI proxy for DeepSeek, ChatGPT, and Claude — pipe any of them into VS Code or Terax using your real browser session. Just paste a fetch().