AI Architect & Co-Founder at RapidClaw
Building the future of AI Agent deployment — from zero to production in 60 seconds.
RapidClaw is an AI Agent deployment platform that makes it dead simple to ship, scale, and monitor AI agents in production.
- agent-router — Lightweight multi-agent task router for Python. Pluggable intent classification, built-in agents, zero required deps.
- agent-memory — Persistent vector memory server for AI agents. SQLite + numpy cosine search, namespaces, TTL, REST API.
- agent-flow — Define, execute, and visualize multi-step AI agent workflows as a DAG. Export to interactive HTML, Mermaid, or JSON.
- agent-bench — Benchmark LLM agents across providers on speed, cost, and quality. Built-in suites for reasoning, coding, writing, and tool-use.
- webhook-agent — Webhook-to-AI-agent bridge. Receive webhooks (Stripe/GitHub/forms), map events to agent handlers, execute automated responses.
- agent-watchdog — Lightweight heartbeat monitor for AI agent loops. Dead man's switch for agent processes with live Rich dashboard.
- agent-cost-cli — Instant LLM cost breakdown for 15+ models from the command line.
pip install git+https://github.com/arcane-bear/agent-cost-cli - awesome-self-hosted-agents — Curated list of open-source tools and frameworks for running AI agents fully self-hosted.
- llm-budget — CLI tool for tracking per-agent LLM spend with budget alerts and 30+ model pricing built in
- hermes-starter — Docker Compose quickstart for Nous hermes-agent with Ollama, config templates, and setup scripts
- agent-probe — Health check sidecar for AI agents. Verifies LLM connectivity, token budgets, tool availability, and response quality beyond simple HTTP 200.
- openclaw-tools — OpenClaw AI Token Cost Calculator and developer tools.
- 🌐 rapidclaw.dev
- 🐦 @rapid_claw


