walrus

Name: walrus
Author: openwalrus

by openwalrus

Verified

The composable agent runtime.

286stars

45forks

Rust

Added 3/16/2026

Installation

# Add to your Claude Code skills
git clone https://github.com/openwalrus/walrus

Getting Started

Guides for using ai agents skills like walrus.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 5/30/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-05-30T15:08:29.228Z",
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is walrus?

walrus is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by openwalrus. The composable agent runtime. It has 286 GitHub stars.

Is walrus safe to use?

Yes. walrus passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install walrus?

Clone the repository with "git clone https://github.com/openwalrus/walrus" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is walrus written in?

walrus is primarily written in Rust. It is open-source under openwalrus on GitHub, so you can review or fork the full source.

Are there alternatives to walrus?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh walrus against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

rust-docs-mcp-server anyclaude

AI Agentsagent-frameworkagent-runtimeaiai-agentcomposabledeveloper-toolllm

First-time install walkthrough for Claude Code, Codex CLI, and ChatGPT.

AI Agentsaibrainstorming

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

227,972

34,864

JavaScript

AI Agentsai-agentsanthropic

The agent that grows with you

212,364

39,138

Python

AI Agentsaiai-agent

View details

Compare

n8n

by n8n-io

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

195,893

59,213

TypeScript

MCP Serversaiapis

View details

Compare

everything-claude-code

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,940

28,768

JavaScript

AI Agentsai-agentsanthropic

View details

Compare

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,031

19,897

Shell

AI Agents

View details

Compare

Walrus

The composable agent runtime. Compact daemon core. Memory, channels, tools — all hooks. Use what you need, skip what you don't.

curl -fsSL https://openwalrus.xyz/install.sh | sh

Or cargo install openwalrus. See the installation guide for details.

Quick Start

# Start the daemon
walrus daemon install

# Chat with your agent
walrus attach

Full config reference: configuration.

How It Works

Walrus is a daemon that runs agents and dispatches tools. The daemon ships with built-in tools (shell, task delegation, memory), MCP server integration, and skills (Markdown prompt files).

Heavier capabilities live outside the daemon as extensions — managed child processes you add or remove in config:

Service	What it does
Search	Meta-search aggregator
Gateway	Telegram adapter

The daemon stays small. Services scale independently.

Learn More

Quickstart — first agent in 2 minutes
Configuration — walrus.toml reference
Providers — connect any LLM
Extensions — how extensions work
Architecture — runtime, event loop, hooks
Why we built OpenWalrus

License

GPL-3.0