sagent — security grade CAUTION, quality 70/100

Security audit verdict: CAUTION · quality 70/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by rekursiv-ai · Codex Skill · ★ 55

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

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

About sagent

sagent🪄 The self-mutating multi-provider coding-agent CLI and typed Python library. Tutorial · Concepts · Providers · Tools · CLI · Sessions · Security · <a href="https://github.com/rekursiv-ai/sagent/blob/main/

agent-frameworkagent-orchestrationagentic-aiagentsaiai-agentsartificial-intelligenceclaude-codecodex-clicoding-agent

Quick Facts

Stars55
Forks13
LanguagePython
CategoryCodex Skill
LicenseApache-2.0
Quality Score69.7301450002061/100
Open Issues1
Last Updated2026-09-19
Created2026-05-05
Platformsclaude-code, cli, codex, gemini, python
Est. Tokens~18k

sagent alternative? Top 6 similar tools

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

  • ai-agent-tools-catalog by GetStream · ⭐ 164

    Explore the must-have external ready-made toolkits to integrate with your AI agents built with Python and Type

  • template-repo by AndrewAltimit · ⭐ 131

    Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interp

  • ralph-starter by multivmlabs · ⭐ 97

    Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.

  • agent-skills by simota · ⭐ 80

    90 specialist AI agents + 3 project-local extensions for Claude Code / Codex CLI / Antigravity CLI (agy). Anth

  • SimpleLLMFunc by NiJingzhe · ⭐ 77

    A simple and well-tailored LLM application framework that enables you to seamlessly integrate LLM capabilities

  • ox by sageox · ⭐ 59

    The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is sagent?

sagent is A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional recursive spawn.. It is categorized as a Codex Skill with 55 GitHub stars.

What programming language is sagent written in?

sagent is primarily written in Python. It covers topics such as agent-framework, agent-orchestration, agentic-ai.

How do I install or use sagent?

You can find installation instructions and usage details in the sagent GitHub repository at github.com/rekursiv-ai/sagent. The project has 55 stars and 13 forks, indicating an active community.

What license does sagent use?

sagent 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 sagent?

The top alternatives to sagent on Agent Skills Hub include ai-agent-tools-catalog, template-repo, ralph-starter. 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 Codex Skill tools