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 gintasz · Agent Tool · ★ 107
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is unigent safe to install? View the security audit →
Unigent The cross-harness agent SDK for TypeScript. Build stateful agent workflows with typed outputs, reusable tools, session forks, and ordinary TypeScript. Examples Install Unigent requires Node
| Stars | 107 |
| Forks | 1 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.0309567960814/100 |
| Last Updated | 2026-07-24 |
| Created | 2026-06-21 |
| Platforms | claude-code, node |
| Est. Tokens | ~18k |
These tools work well together with unigent for enhanced workflows:
Looking for a unigent alternative? If you're comparing unigent 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.
将 AI 命令行工具以最为原生的方式，集成到微信 ClawBot / 企业微信 bot 中，目前支持集成 Codex、Claude Code、OpenCode、Pi Agent。 支持微信和本地终端线程（thread/s
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, an
📼 Declarative AI agent environment manager, written in Rust
Code Agent++ 面向 AI 编程 Agent 的外挂式增强与可靠性工程层。 Code Agent++ 不做另一个代码生成 Agent，也不替代 Codex、OpenCode、Claude Code、Curs
Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.
Ralph Wiggum meet Kanban! Ralph style execution for [Claude Code, Codex, Pi, Cursor]. One task per iteration,
Explore other popular agent tool tools:
unigent is Build stateful agent workflows with typed outputs, reusable tools, session forks, and ordinary TypeScript.. It is categorized as a Agent Tool with 107 GitHub stars.
unigent is primarily written in TypeScript. It covers topics such as agent, ai, ai-agent.
You can find installation instructions and usage details in the unigent GitHub repository at github.com/gintasz/unigent. The project has 107 stars and 1 forks, indicating an active community.
unigent is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to unigent on Agent Skills Hub include CLI-WeChat-Bridge, entroly, kasetto. 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: