No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by zevorn · Codex Skill · ★ 650
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is rt-claw safe to install? View the security audit →
Making AI Assistants Cheap Again 中文 | English RT-Claw is an OpenClaw-inspired intelligent assistant for embedded devices. Multi-OS support via OSAL (FreeRTOS, RT-Thread, Zephyr and Linux). Build swarm intelligence with networked nodes. ESP32-S3 WiFi support adapted from MimiClaw. Deploy your own AI assistant on hardware that costs just one dollar — seamlessly integrated into your daily workflow, efficiently bridging the digital and physical worlds. <img src="images/demo.png" alt="RT-Claw Dem
| Stars | 650 |
| Forks | 48 |
| Language | C |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 63.8538910544794/100 |
| Open Issues | 3 |
| Last Updated | 2026-05-26 |
| Created | 2026-03-11 |
| Est. Tokens | ~736k |
These tools work well together with rt-claw for enhanced workflows:
Looking for a rt-claw alternative? If you're comparing rt-claw with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An open-source AI assistant framework with skills and agent architecture
A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a
A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect you
Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG.
Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear
AI agent microservice
Explore other popular codex skill tools:
rt-claw is Making AI Assistants Cheap Again!. It is categorized as a Codex Skill with 650 GitHub stars.
rt-claw is primarily written in C. It covers topics such as ai, assistant, cheap.
You can find installation instructions and usage details in the rt-claw GitHub repository at github.com/zevorn/rt-claw. The project has 650 stars and 48 forks, indicating an active community.
rt-claw is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to rt-claw on Agent Skills Hub include openakita, poco-agent, clawsec. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: