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 princezuda · Codex Skill · ★ 279
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is safestclaw safe to install? View the security audit →
SafestClaw 🐾 The zero-cost alternative to OpenClaw. No LLM required, though it is optional. No required API bills. Minimal attack surface. Runs on any machine. ONE HUNDRED STARS — We hit ONE HUNDRED stars on GitHub! This milestone is our biggest update since our original release. It brings: Real Research, Simple AI Setup, and Smart Learning. Research now searches arXiv and Semantic Scholar for real academic papers, asks Wolfram Alpha for computational answers. instantly configures Anthropic (or any provider) — or for free Ollama. The parser auto-corrects typos, converts word-numbers ("one" → 1), and learns from your mistakes automatically. See the new features below. Previous milestone: Fuzzy Learning & Personalization. While OpenClaw users are burning $200/day and $3,600/month on API tokens, SafestClaw delivers 90% of the functionality using traditional programming — rule-based parsing, ML pipelines, and local-first tools. Your API bill: $0. Forever. If you choose to use the language models for blogging, coding and research, then yeah, you'll have a bill, but you can also do all of that without a
| Stars | 279 |
| Forks | 33 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 64.6013315001132/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-19 |
| Created | 2026-02-02 |
| Platforms | python |
| Est. Tokens | ~79k |
These tools work well together with safestclaw for enhanced workflows:
Looking for a safestclaw alternative? If you're comparing safestclaw 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.
A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdb
Natively - Free open-source AI interview copilot & meeting assistant. The best Cluely alternative, Final Round
Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templ
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
MCPSDK.dev(ToolSDK.ai)'s Awesome MCP Servers and Packages Registry and Database with Structured JSON configura
Explore other popular codex skill tools:
safestclaw is Safestclaw is the alternative to openclaw.. You can naturally chat with it via text and voice, and you can choose not to use a language model., By default it picks up on intent and semantics.. No pro. It is categorized as a Codex Skill with 279 GitHub stars.
safestclaw is primarily written in Python. It covers topics such as agentic-ai, ai, ai-agent.
You can find installation instructions and usage details in the safestclaw GitHub repository at github.com/princezuda/safestclaw. The project has 279 stars and 33 forks, indicating an active community.
safestclaw is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to safestclaw on Agent Skills Hub include awesome-openclaw, natively-cluely-ai-assistant, dexto. 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: