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 AtomicBot-ai · MCP Server · ★ 2.6k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is atomic-agent safe to install? View the security audit →
atomic-agent A local-first operator agent runtime that squeezes the maximum out of models on your own machine — turboquant , curated quants, and a runtime engineered for local inference. The machine on your desk, not in somebody else's cloud. ![Tauri sidecar](https://img.shields.io/badge/Tauri-sidecar-24C8DB?l
| Stars | 2,642 |
| Forks | 256 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 66.5980656773535/100 |
| Open Issues | 30 |
| Last Updated | 2026-10-02 |
| Created | 2026-04-21 |
| Platforms | browser, cli, mcp, node |
| Est. Tokens | ~18k |
These tools work well together with atomic-agent for enhanced workflows:
Looking for a atomic-agent alternative? If you're comparing atomic-agent 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.
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
Zero-Config Code Flow for Claude code & Codex
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make
The pretty much "official" DSPy framework for Typescript
A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdb
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
Explore other popular mcp server tools:
atomic-agent is Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.. It is categorized as a MCP Server with 2.6k GitHub stars.
atomic-agent is primarily written in TypeScript. It covers topics such as agents, ai-agent, browser-automation.
You can find installation instructions and usage details in the atomic-agent GitHub repository at github.com/AtomicBot-ai/atomic-agent. The project has 2.6k stars and 256 forks, indicating an active community.
atomic-agent is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to atomic-agent on Agent Skills Hub include voltagent, zcf, gptme. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: