2026年3月26日Agent-OperableOpen SourceAPITool

Jentic Mini: Open Source API Execution Layer Gives Agents Safe Access to 10,000+ APIs

Jentic has launched Jentic Mini, a free, open source, self-hosted API execution layer that gives AI agents safe access to over 10,000 APIs with fine-grained permissions and a single killswitch.

Released on March 25, Jentic Mini addresses a fundamental problem: agents need to call real APIs, but unrestricted access is dangerous. Jentic Mini provides an AI-curated catalog of 10,000+ APIs and workflows with per-API permission controls, minimal credential exposure, and an instant killswitch that shuts down all agent data access.

While built primarily for OpenClaw, Jentic Mini works with other general-purpose agents including NemoClaw. Jentic is also already available as a verified connector in Claude, giving users secure access to connected tools and APIs directly through Anthropic's assistant.

The catalog itself is expanding continuously, with agents actively curating and adding new APIs over time. Jentic Mini is available on GitHub and via the Jentic website, giving developers a lightweight way to self-host the safety and control layer around their agent API access.

https://jentic.com/mini
https://github.com/jentic
← 上一篇
Cloudflare Dynamic Workers:比容器快 100 倍的 Agent 沙箱执行环境
下一篇 →
Jentic Mini:开源 API 执行层,让 Agent 安全接入 10,000+ API
← 返回所有文章

评论

加载中...
>_