wanta — security grade SAFE, quality 59/100

Security audit verdict: SAFE · quality 59/100

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 oomol-lab · Agent Tool · ★ 75

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

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

About wanta

English · 简体中文 · 日本語 · Español · 한국어 Wanta An open desktop host for your models, your agents, your work apps, and your teams. Run the built-in Agent with Wanta-hosted models or your own OpenAI-compatible API key. Or bring Claude Code, Codex, and Grok with their existing local accounts, native model catalogs, and usage quotas. Wanta gives every supported Agent one cross-platform workspace for local tools, Skills, browser and knowledge access, governed connections to 1,400+ popular apps, visible execution, and artifacts—so the services you already use can become part of the same Agent workflow. Website · OpenConnector · Documentation · Development Guide From a connected-service task to a reusable, interactive artifact in one workspace. BYOK Models · BYOA Agents · 1,400+ Popular Apps

agentic-aiai-agentbyokcross-platformdesktop-agentelectronhuman-in-the-loopllmopencodeopenconnector

Quick Facts

Stars75
Forks14
LanguageTypeScript
CategoryAgent Tool
LicenseApache-2.0
Quality Score58.6623827183754/100
Open Issues1
Last Updated2026-09-20
Created2026-06-12
Platformsnode
Est. Tokens~19k

wanta alternative? Top 6 similar tools

Looking for a wanta alternative? If you're comparing wanta with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • pie-ai-agent by WiseriaAI · ⭐ 182

    Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skil

  • palot by ItsWendell · ⭐ 187

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

  • CaoGen by opengenesishq · ⭐ 121

    CaoGen — a vendor-neutral, local-first AI work desktop. Multi-provider agent runtime, GUI automation, MCP, Git

  • openclaw-desktop by rshodoskar-star · ⭐ 119

    🖥️ A native desktop client for OpenClaw premium UI experience without the browser. Built with Electron + Rea

  • cetus by drewnekota · ⭐ 146

    One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher

  • Image-MetaHub by LuqP2 · ⭐ 317

    Local-first AI image organizer and generative media library manager for ComfyUI, A1111, InvokeAI & more. Searc

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is wanta?

wanta is An open-source desktop AI agent foundation powered by OpenCode and connected through OpenConnector, with local tools, permission controls, and artifacts.. It is categorized as a Agent Tool with 75 GitHub stars.

What programming language is wanta written in?

wanta is primarily written in TypeScript. It covers topics such as agentic-ai, ai-agent, byok.

How do I install or use wanta?

You can find installation instructions and usage details in the wanta GitHub repository at github.com/oomol-lab/wanta. The project has 75 stars and 14 forks, indicating an active community.

What license does wanta use?

wanta is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to wanta?

The top alternatives to wanta on Agent Skills Hub include pie-ai-agent, palot, CaoGen. 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 Agent Tool tools