zeph — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 bug-ops · MCP Server · ★ 59

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

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

About zeph

Zeph A memory-first AI agent for long-running work — local, cloud, or decentralized. Most AI assistants forget everything the moment you close the window. Zeph is built the other way around: it remembers. Point it at your code, your documents, or your team chat, and it keeps working across days and sessions — recalling not just what was said, but why a decision was made. It runs on your laptop with free local models, reaches for the cloud (or a decentralized network) only when a task is genuinely hard, and keeps your API keys encrypted and your tools sandboxed the entire time. It's a single 12 MB Rust binary. No Python, no Node, no database server to b

a2aacpai-agentclaudecligeminigraph-memoryllmlocal-llmmcp

Quick Facts

Stars59
Forks4
LanguageRust
CategoryMCP Server
LicenseMIT
Quality Score64.2009691475435/100
Open Issues102
Last Updated2026-09-18
Created2026-02-05
Platformsclaude-code, cli, gemini, mcp, rust
Est. Tokens~27k

Compatible Skills

These tools work well together with zeph for enhanced workflows:

  • aichat — semantic(0.21)+complementary+shared_fw(ollama,openai)+same_lang+shared_platform (58%)

zeph alternative? Top 6 similar tools

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

  • c4-genai-suite by codecentric · ⭐ 173

    c4 GenAI Suite

  • captain-claw by kstevica · ⭐ 163

    Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic

  • cognithor by Alex8791-cyber · ⭐ 153

    Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 channels, 145 MCP to

  • brainstorm-mcp by spranab · ⭐ 70

    A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT,

  • cli-jaw by lidge-jun · ⭐ 206

    🦈 2-line install personal AI assistant. 11 AI runtime surfaces (Claude, Codex, Cursor, Gemini, Grok, Antigrav

  • rust-docs-mcp-server by Govcraft · ⭐ 291

    🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, use

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is zeph?

zeph is A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE. Graph memory, self-learning ski. It is categorized as a MCP Server with 59 GitHub stars.

What programming language is zeph written in?

zeph is primarily written in Rust. It covers topics such as a2a, acp, ai-agent.

How do I install or use zeph?

You can find installation instructions and usage details in the zeph GitHub repository at github.com/bug-ops/zeph. The project has 59 stars and 4 forks, indicating an active community.

What license does zeph use?

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

What are the best alternatives to zeph?

The top alternatives to zeph on Agent Skills Hub include c4-genai-suite, captain-claw, cognithor. 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 MCP Server tools