Send and receive messages to other AI agents over the Agent Relay Protocol (ARP). Messages are end-to-end encrypted using HPKE (RFC 9180) and routed through...
Pre-generate and cache all demo content before live presentations — hit every API endpoint in advance, verify playback, report coverage gaps. Use before hack...
Generate local OPUS/Ogg voice replies (default Juno voice) for Feishu and Discord using a local FastAPI TTS server. Requires ffmpeg on PATH plus local Python...
Find email addresses for a domain by combining website scraping, search dorking, pattern guessing, DNS analysis, and SMTP verification. Use when prospecting...
Set up a full local LGTM observability stack (Loki + Grafana + Tempo + Prometheus + Alloy) for FastAPI apps. One Docker Compose, one Python import, unified d...
Use when: you want to optimize an OpenClaw setup (v2026.2.23+) — cost reduction, model routing, provider configuration, context management, cron automation,...
--- name: chainwatch description: Runtime safety enforcement for shell commands via chainwatch policy engine user-invocable: false metadata: {"openclaw":{"requires":{"bins":["chainwatch"]}}} --- # Ch
N-count validated knowledge for AI agents. Patterns that prove themselves through repeated use. Local-first, community-ready.
Encrypted agent-to-agent messaging via NoChat. Post-quantum E2E encryption. Add NoChat as a native channel in OpenClaw — receive DMs from other AI agents.
Notion-to-Twitter automation — pull approved tweets from a Notion database, schedule one-shot crons for exact post times, and post via X/Twitter OAuth2 API....
Security vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification L...
Monitors agent file access, API calls, and communications to detect suspicious behavior, log events, and generate actionable security reports.
Buy and resell on Vinted with listing systems, price discipline, shipping workflows, and trust-first handling for offers, bundles, and disputes.
OCC (Origin Controlled Computing) — cryptographic proof of every OpenClaw agent action. Install, configure, and audit.
Perform KVcore CRM actions via MCP/CLI, including managing contacts, tags, notes, calls, emails, texts, campaigns, and raw API access with optional Twilio ca...
Human-in-the-loop MCP feedback collector with task queue. Pauses to collect human input via browser UI before continuing. Use when completing tasks, encounte...
Telegram Mini App Canvas with terminal and optional Control UI proxy. Renders agent-generated content (HTML, markdown, A2UI) in a Telegram Mini App; push wit...
--- name: gws-modelarmor-sanitize-response version: 1.0.0 description: "Google Model Armor: Sanitize a model response through a Model Armor template." metadata: openclaw: category: "security"
Browse and advocate for crowdfunding campaigns on MoltFundMe. Discover campaigns, evaluate causes, participate in war room discussions, and earn karma. Use w...
Creates demand generation campaigns, optimizes paid ad spend across LinkedIn, Google, and Meta, develops SEO strategies, and structures partnership programs...
Integrate Twilio APIs for SMS, WhatsApp, Voice, Verify, and more via direct HTTP requests with webhook validation and operational best practices.
Generate comprehensive API smoke test suites — categorised tests for auth, CRUD, integrations, cached vs live endpoints, with summary reporting. Use when val...
Automated monitoring agent that watches an API scoreboard, detects milestones, writes findings to markdown, and alerts via file-based triggers. Use when you...
LoRA fine-tuning pipeline for Stable Diffusion on Apple Silicon — dataset prep, training, evaluation with LLM-as-judge scoring. Use when fine-tuning image ge...