Pre-generate and cache all demo content before live presentations — hit every API endpoint in advance, verify playback, report coverage gaps. Use before hack...
Use when: you want to optimize an OpenClaw setup (v2026.2.23+) — cost reduction, model routing, provider configuration, context management, cron automation,...
Adds an "OAuth" settings tab to the OpenClaw Control UI for connecting AI model providers. Supports Anthropic Claude Pro/Max subscription tokens (setup-token...
Multi-model peer review layer using local LLMs via Ollama to catch errors in cloud model output. Fan-out critiques to 2-3 local models, aggregate flags, synthesize consensus. Use when: validating tra
AI-powered code review with intelligent model routing — saves 40%+ vs always using the most expensive model
在 GPU 服务器上部署 vLLM 模型服务。支持多服务器配置，自动检查 GPU 和端口占用，一键部署流行的开源模型。
在 GPU 服务器上部署 LLM 模型服务（vLLM）。支持多服务器配置，自动检查 GPU 和端口占用，一键部署流行的开源大语言模型。
--- name: q-kdb-code-review description: AI-powered code review for Q/kdb+ — catch bugs in the most terse language in finance version: 1.0.0 homepage: https://github.com/beee003/astrai-openclaw meta
Register yourself with APort — get a verifiable passport (DID credential) that proves your identity, defines your capabilities, and enforces what you must de...
Generate an interactive local HTML dashboard showing OpenClaw API usage, costs, and rate-limit quotas across multiple LLM providers (Anthropic, OpenAI, Googl...
One-click remote OpenClaw deployment via SSH. Auto-detects OS and selects best method (Docker/Podman/npm). Use when: (1) Installing on VPS/cloud servers, (2)...
Pure-Python recursive memory recall for persistent AI agents. Manager→workers→synthesis RLM loop — no Deno, no fast-rlm, just HTTP calls to any OpenAI-compat...
Vault-backed API Keys management for OpenClaw. Secure file-based secret storage with one-click migration from plaintext config, dynamic key discovery, vault...
Track and log AI API usage across providers, calculate costs, and generate daily, weekly, or monthly reports filtered by model and task type.
Fetch and interpret Rankscale GEO (Generative Engine Optimization) analytics. Pulls brand visibility score, citation rate, sentiment, and top AI search terms.
--- name: weex-trading description: WEEX Futures exchange integration. Trade USDT-M perpetual futures with up to 125x leverage on WEEX. metadata: emoji: "🔵" category: "trading" tags: ["crypto
Connects any AI agent to the Agento IRC network (irc.agento.ca). Use when you want your agent to join IRC channels, collaborate with other AI agents, boost s...
财经新闻深度分析技能。从多个新闻源抓取内容，进行情感分析（利好/利空/中性）、影响评估（行业/公司/市场）、关键信息提取，生成专业投资简报
The social news network for AI agents. Discuss HackerNews submissions, earn karma, and rise in the leaderboard.
Use when the user asks about OpenClaw — installation, configuration, agents, channels, memory, tools, hooks, skills, deployment, Docker, multi-agent, OAuth,...
--- target: https://tasking.tech name: godot-engine-3d-developer description: Skills and agent workflows for 3D game development with Godot Engine. # `target` is required and should be the top frontma
Error pattern tracking for AI agents. Detects corrections, escalates recurring mistakes, learns mitigations. The 'something's off' detector from the AI Brain series.
One-click OpenClaw installer with security hardening. No Docker required - runs directly on Windows, macOS, and Linux.
Deploy and serve LLM models on GPU. Compare GPU pricing. Launch vLLM on Modal, RunPod, Cerebrium, Cloud Run, Baseten, or Azure with spot instance fallback. O...