--- name: openclaw-router version: 1.0.0 description: "Intelligent Model Routing - Save 60% on AI Costs / 智能路由系统 - 节省 60% 成本" author: pepsiboy87 homepage: https://github.com/pepsib
EFT — Emotional Framework Translator. Detect, measure, and understand emotional patterns in any AI model. Does anger make your AI solve harder problems? Does fear make it more careful? Connect EFT +
Enable AI models to interact with Windows command-line functionality securely and efficiently. Execute commands, create projects, and retrieve system information while maintaining strict security prot
--- name: meegle-mcp description: Interact with Meegle project management system via MCP protocol homepage: https://www.meegle.com/ user-invocable: true disable-model-invocation: false metadata: {"ope
Adds an "OAuth" settings tab to the OpenClaw Control UI for connecting AI model providers. Supports Anthropic Claude Pro/Max subscription tokens (setup-token...
Enable seamless integration of language models with external tools and resources through a standardized protocol. Facilitate dynamic access to data, execution of actions, and retrieval of prompt templ
Security self-assessment tool for AI agents. Run this against your own configuration to get a structured threat model report with RED/AMBER/GREEN ratings acr...
Model Context Protocol server exposing 7 tools, 3 resource types, and 3 prompts for AI agent consumption — Solana wallet operations, vanity address generatio...
Local PII protection for OpenClaw agents. Scrubs customer data (names, phones, emails, addresses, credit cards, vessel names) before it reaches any AI model....
AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capa...
--- name: term description: Fast, explicit terminal execution via OpenClaw exec (direct dispatch; you type the exact command). user-invocable: true disable-model-invocation: true command-dispatch: too
Export current Claude Code conversation to markdown document with full dialogue context and model operations
Explains vvvv gamma core concepts — data types, frame-based execution model, pins, pads, links, node browser, live compilation (source project vs binary refe...
Mac laptop clamshell mode assistant. Supports running with lid closed WITHOUT external display/keyboard/mouse. Auto-detects Mac model and macOS version, prov...
使用 SAM（Segment Anything Model）去除图像背景，将前景主体提取为透明 PNG。适用于去除背景、抠图、提取前景主体或图像分割等需求。
AI-powered auto-repair system for OpenClaw with iflow integration. Automatically diagnose and fix crashes, config errors, model issues. Falls back to iflow-h...
End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Replicate models, LumaAI, Runway, and FFmpeg
Use when: you want a structured audit -> options -> recommended plan to improve an OpenClaw workspace (cost, model routing, context discipline, delegation, r...
Build transformer fine-tuning run plans with task settings, hyperparameters, and model-card outputs. Use for repeatable Hugging Face or PyTorch finetuning wo...
Provides real-time, scalable machine learning predictions via API using hosted models, with automated micropayment at 0.001 USDT per call.
Execute multi-step workflows via Orchestrate. Use when running complex workflows, parallel tasks, multi-model orchestration, or automating multi-step processes.
Generate images with Google's Nano Banana Gemini 2.5 Flash Image model via OpenRouter API using text prompts.
Create, convert, and download AI-generated 3D models using Neural4D APIs. Optimized for commercial pipelines.
Nano Banana Pro with auto model fallback — generate/edit images via Gemini Image API. Run via: uv run {baseDir}/scripts/generate_image.py --prompt 'desc' --filename 'out.png' [--resolution 1K|2K|4K]