walrus — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

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 openwalrus · Codex Skill · ★ 91

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

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

About walrus

Crabtalk [![Crates.io][crates-badge]][crates] [![Docs][docs-badge]][docs] [![Discord][discord-badge]][discord] Agent daemon. Runs agents, dispatches tools, connects to MCP servers. Start it, talk to it, extend it with packages. Or and use it to pull the rest. See the [installation guide][install] for details. Quick Start Full config reference: . How It Works The daemon ships with built-in tools (shell, task delegation, memory), MCP server integration, and skills (Markdown prompt files). Apps are agent-powered experiences and standalone services built on top of the daemon — independent binaries that connect via auto-discovery. Learn More [The Crabtalk Book][book] — manifesto, architecture, and design RFCs Configuration — config.toml reference Contributing — architecture, layering, and data flow License MIT [crates-badge]: https://img.shields.io/crates/v/crabtalk.svg

agentagenticagentic-workflowaiopenclaw

Quick Facts

Stars91
Forks13
LanguageRust
CategoryCodex Skill
LicenseMIT
Quality Score61.6028962319126/100
Open Issues2
Last Updated2026-03-10
Created2025-01-01
Platformsrust
Est. Tokens~148k

walrus alternative? Top 6 similar tools

Looking for a walrus alternative? If you're comparing walrus 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 walrus?

walrus is Core abstractions for your agentic workflow. It is categorized as a Codex Skill with 91 GitHub stars.

What programming language is walrus written in?

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

How do I install or use walrus?

You can find installation instructions and usage details in the walrus GitHub repository at github.com/openwalrus/walrus. The project has 91 stars and 13 forks, indicating an active community.

What license does walrus use?

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

What are the best alternatives to walrus?

The top alternatives to walrus 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