Search

Local cost/complexity-aware model router for Oh My Pi, backed by OpenRouter

Claude Code decides which skills a task needs, installs them safely from skills.sh under a trust policy, then solves the task.

Validate agent skills against 7 standards (agentskills.io, Anthropic, Hermes, skills.sh, Claude Code, Agent Plugins, OpenAI Codex) in one command.

CarlyEmail's email tools for the Vercel AI SDK, LangChain, and any other agent framework.

TypeScript SDK for FerricStore and FerricFlow

DeepSeek Harness 自动化任务与调度中心插件 (WorkBuddy 原生交互对齐版)

Scaffold the agent-driven development workflow into a project

Pipeline node library for Nexploy — descriptors, executors and configuration panels.

Codex-backed web search, image generation, and image understanding tools for the DeepSeek Harness.

Lets a text-only agent call a multimodal model mid-task: the vision tool sends one image file to Qwen, Kimi, OpenAI, Claude, Gemini or a self-hosted endpoint and returns structured evidence — summary, verbatim OCR, layout, entities, and what the model cou

DSH Web 插件：调用智谱 GLM 视觉模型分析图片（analyze_image 工具 + 插件设置卡片）。

Locked env vars and secrets, shared safely with your team, from the terminal.

Aura Vision — free vision OCR plugin for DeepSeek Harness web profile: Zhipu GLM-4V-Flash (free tier), adaptive tile recognition for long documents, history with favorites and Markdown/Excel/Word/PNG export.

Native OpenCode V2 plugin that gives text-only models vision: relays image parts to Gemini or any OpenAI-compatible provider (OpenAI, Groq, OpenRouter, Ollama...) and replaces them with detailed text analyses before the model dispatch — works with any mod

DeepSeek Harness 全能插件：识别/生图/改图一体化，无需切换模型——用常规 DeepSeek 模型即可自动调用视觉与生图模型（gemini_vision / gemini_generate_image / gemini_optimize_image）。多后端：Gemini 原生 + 任意 OpenAI 兼容服务（GPT-4o、Qwen-VL、GLM-4V、Moonshot、gpt-image、DALL-E、Flux、Stable Diffusion、OpenRouter、硅基流动、各类中转

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

On-the-fly image processing for Wappler with Sharp - resize, convert formats, and intelligent caching

esh — embeddable shell runtime for JavaScript. Shell syntax + virtual fs, runs in browser (OPFS persistence), Node, and workers.

Ядро Axon: персональный AI-агент, который живёт на вашей машине

An agent-independent prompt, multi-language code-index, cleanup, and verification companion with optional Codex hooks.