Search

Alias for claude-real-video — let any LLM actually watch a video (scene-aware frames + transcript).

Cache-aware prompt structure optimizer + local cost/usage logger for LLM apps.

EvoLink API examples and agent skill for Nanobanana 2 Lite Image Generation.

Agent skill aggregator. Install a curated set of agent skills across Claude Code, Codex, opencode, and Gemini with manifest-backed safety.

Agent skill for the free StoryKit design library (embed charts/widgets/themes with your data + colors) and BYOM visual essays — your model authors, StoryKit designs, hosts and shares. No key needed.

Obsidian 볼트 기반 LLM Wiki — Claude Code + OpenCode 양쪽에서 사용 가능. CC 플러그인 구조(commands/skills/agents)를 OC config 훅으로 주입.

Windsurf to OpenAI + Anthropic compatible API proxy. Turns Windsurf's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Grok, Qwen, Kimi, GLM, SWE) into dual-protocol API endpoints. Zero npm deps.

OneClear industrial dust-collection filter-media presales skill installer.

Claude Code skill: analyze images and videos via Fmode API vision models (api.fmode.cn). Single-pass and multi-pass focused analysis with structured JSON output. Auto-reads token from FMODE_API_TOKEN, ~/.fmode/config.json, project .fmode/config.json, or A

Claude Code skill: 录音文件转写（讯飞 LFASR）通过 Fmode 网关 /api/listen/transcribe 完成。讯飞凭据仅服务端持有，客户端只需 fmode token，服务端按音频时长计费。提供 `npx fmode-listen transcribe` 直连命令 + Claude Code 技能安装器。

Cache Machine — scoped Server Connect caching for Wappler (per user, IP, or custom key). Redis optional.

Eleventy boilerplate with per-page SCSS/JS pipeline, esbuild bundling, multi-framework CSS support and a built-in page management CLI

Shows prompt processing progress from llama.cpp's SSE stream

Belong — embeddable React AI assistant dock. Mount <BelongWidget> in your app tree with getToken dependency-injection auth.

Visual Database Designer for MySQL/MariaDB - Design, visualize, and manage your database schema with ease

Zep long-term memory for the Vercel AI SDK — a middleware that injects user context, plain persist/retrieve helpers, and model-callable tools over Zep's temporal Context Graph.

AI API observability SDK — track tokens, cost, latency and errors across OpenAI, Anthropic and more

Fireworks AI provider extension for pi - Access Kimi, MiniMax, GLM, DeepSeek, and GPT-OSS models through the Fireworks AI API

An enterprise-grade, database-agnostic password policy engine for Node.js

Evaluation version of GRID's high-performance spreadsheet engine, Apiary