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 8treenet · Codex Skill · ★ 65
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is raven safe to install? View the security audit →
Raven open source · self-hosted · ai harness Website · Live Preview · Discord · 中文 Stop Buildi
| Stars | 65 |
| Forks | 5 |
| Language | Go |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 69.2366996454525/100 |
| Open Issues | 3 |
| Last Updated | 2026-07-25 |
| Created | 2026-06-15 |
| Platforms | go |
| Est. Tokens | ~16k |
Looking for a raven alternative? If you're comparing raven with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An introduction to the world of AI Agents
Make AI actually work for you - A personal agent that writes its own tools and repairs itself.
A ReAct-Based Highly Robust Autonomous Agent (Harness) Framework.
Bridgic is the next-generation agent development framework for building intelligent systems.
HotPlex — Unified access layer for AI Coding Agent.
The Runtime Security Layer for OpenClaw/Hermes-agent, the essential safety harness for PII & sensitive credent
Explore other popular codex skill tools:
raven is Raven is a self-hostable team Agent platform providing isolated workspaces and unified runtimes for multi-agent workflows.. It is categorized as a Codex Skill with 65 GitHub stars.
raven is primarily written in Go. It covers topics such as agent, ai-agent, deepseek.
You can find installation instructions and usage details in the raven GitHub repository at github.com/8treenet/raven. The project has 65 stars and 5 forks, indicating an active community.
raven is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to raven on Agent Skills Hub include oreilly-ai-agents, Agenvoy, Autono. 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: