Deus — security grade CAUTION, quality 71/100

Security audit verdict: CAUTION · quality 71/100

Flagged: opens a tunnel service. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by sliamh11 · Agent Tool · ★ 50

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

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

About Deus

A personal AI that understands you - not just recalls things you've said. It learns what you care about, how you think, and what you'll actually find useful. The longer you use it, the more it feels like it gets you. Everything runs on your computer. Your data stays yours. What it does Understands you - It doesn't just store memories - it breaks conversations into facts, indexes by meaning, and builds a model of what you care about. Ask about something from three weeks ago and it recalls the details, even if you don't remember what you called it. Works in any language — Hebrew, Arabic, and other non-Latin scripts included. (95% recall on the LongMemEval benchmark; multilingual reranker active.) Adapts to how you think - Scores its own responses, generates self-critiques, and rewrites its system prompt based on what worked. Tone, judgment, the kind of suggestions it surfaces - all of it improves at the personality level.

ai-assistantai-memoryclaude-codecontainer-isolationpersistent-memoryself-improving-aisemantic-memorysemantic-search

Quick Facts

Stars50
Forks4
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score70.9008782412928/100
Open Issues33
Last Updated2026-08-16
Created2026-03-21
Platformsclaude-code, python
Est. Tokens~17k

Deus alternative? Top 6 similar tools

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

  • roampal-core by roampal-ai · ⭐ 50

    Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo

  • omega-memory by omega-memory · ⭐ 218

    Persistent memory for AI coding agents

  • zer0dex by hermes-labs-ai · ⭐ 60

    A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic

  • yantrikdb-server by yantrikos · ⭐ 173

    Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memorie

  • openclaw-config by TechNickAI · ⭐ 75

    Give your AI assistant memory, skills, and autonomy. Persistent memory, integration skills, and autonomous wor

  • yantrikdb by yantrikos · ⭐ 63

    Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, kno

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Deus?

Deus is A token-efficient open-source AI assistant that remembers, adapts, and improves — secured, self-hosted, and entirely yours.. It is categorized as a Agent Tool with 50 GitHub stars.

What programming language is Deus written in?

Deus is primarily written in Python. It covers topics such as ai-assistant, ai-memory, claude-code.

How do I install or use Deus?

You can find installation instructions and usage details in the Deus GitHub repository at github.com/sliamh11/Deus. The project has 50 stars and 4 forks, indicating an active community.

What license does Deus use?

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

What are the best alternatives to Deus?

The top alternatives to Deus on Agent Skills Hub include roampal-core, omega-memory, zer0dex. 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