cydonia — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 clearloop · Codex Skill · ★ 97

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is cydonia safe to install? View the security audit →

About cydonia

[!NOTE] This repo is now public archive. The project is now called openwalrus/walrus. Walrus Run autonomous agents with built-in LLM inference. No API keys. No cloud. Just one binary. Or install with Cargo: What It Does Local inference — runs LLMs on your machine (Metal on macOS, CUDA on Linux) Persistent memory — agents remember across sessions (SQLite + FTS5) Built-in tools — file I/O, shell, MCP servers, cron scheduling Multi-channel — talk to your agents from the terminal, Telegram, or Discord Skills — extend agents with Markdown prompt files, no code needed Quick Start Models are configured in . Point it at a local model or any OpenAI-compatible API: Cloud Providers walrus works with OpenAI, Anthropic, DeepSeek, and other OpenAI-compatible APIs. Local inference is the default — cloud is opt-in. License GPL-3.0

agentagenticagentic-workflowaiopenclaw

Quick Facts

Stars97
Forks14
LanguageRust
CategoryCodex Skill
LicenseMIT
Quality Score65.3719313242768/100
Open Issues1
Last Updated2026-03-11
Created2025-01-01
Platformsrust
Est. Tokens~146k

Compatible Skills

These tools work well together with cydonia for enhanced workflows:

  • walrus — semantic(1.00)+same_lang+similar_pop+shared_platform (55%)

cydonia alternative? Top 6 similar tools

Looking for a cydonia alternative? If you're comparing cydonia 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.

  • SimpleLLMFunc by NiJingzhe · ⭐ 77

    A simple and well-tailored LLM application framework that enables you to seamlessly integrate LLM capabilities

  • agents by astronomer · ⭐ 445

    AI agent tooling for data engineering workflows.

  • agent-builder by strands-agents · ⭐ 424

    An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder c

  • agnix by agent-sh · ⭐ 422

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • volcano-agent-sdk by Kong · ⭐ 406

    🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few

  • skillz by intellectronica · ⭐ 398

    An MCP server for loading skills (shim for non-claude clients).

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is cydonia?

cydonia is Core abstractions for your agentic workflow. It is categorized as a Codex Skill with 97 GitHub stars.

What programming language is cydonia written in?

cydonia is primarily written in Rust. It covers topics such as agent, agentic, agentic-workflow.

How do I install or use cydonia?

You can find installation instructions and usage details in the cydonia GitHub repository at github.com/clearloop/cydonia. The project has 97 stars and 14 forks, indicating an active community.

What license does cydonia use?

cydonia is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to cydonia?

The top alternatives to cydonia on Agent Skills Hub include SimpleLLMFunc, agents, agent-builder. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools