Maintainer of this skill?
Automated security scan — not a certification.
iPad-first, open-source iOS AI Agent with native on-device 3D/CAD editing, iPhone support and Android alpha. On-device Linux, terminal, Python/Node.js, Git and web previews; BYOK AI, Notes, Office, Canvas, voice, Skill Hub and supported local models on iOS. 开源设备端 AI 智能体工作台。
# Add to your Claude Code skills
git clone https://github.com/JiangNanGenius/floe-agentGuides for using ai agents skills like floe-agent.
Last scanned: 9/24/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-24T09:01:40.319Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how floe-agent compares with popular alternatives.
floe-agent is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by JiangNanGenius. iPad-first, open-source iOS AI Agent with native on-device 3D/CAD editing, iPhone support and Android alpha. On-device Linux, terminal, Python/Node.js, Git and web previews; BYOK AI, Notes, Office, Canvas, voice, Skill Hub and supported local models on iOS. 开源设备端 AI 智能体工作台。. It has 448 GitHub stars.
Yes. floe-agent passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/JiangNanGenius/floe-agent" and add it to your Claude Code skills directory (see the Installation section above).
floe-agent is primarily written in Swift. It is open-source under JiangNanGenius on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh floe-agent against similar tools.
No comments yet. Be the first to share your thoughts!
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
Install · Features · Demo · Docs · Develop · Contribute
From installation to your first result · Full manual
From installation to your first result · Full manual
Choose an installation channel on the website. Explore the iOS AI Agent workspace for iPad and iPhone. Check current status and the installation page for each channel’s version, region and eligibility.
https://raw.githubusercontent.com/JiangNanGenius/floe-agent/main/feather.json
| Channel | Before you install |
|---|---|
| iOS / iPadOS · TestFlight | Apply for beta access on the website. Available builds and eligibility appear in TestFlight. |
| iOS / iPadOS · Feather / AltStore | Install the corresponding app, use a button above to add the source, then sign with your own setup. |
| iOS / iPadOS · GitHub IPA | Download the IPA and checksum from Releases. The IPA is unsigned and requires your own signing. |
| Android alpha | Android 9+ (ARM64). Install the signed APK from the Android release. GitHub builds check for updates and guide download, verification and system installation, using a smaller patch when available. The alpha includes BYOK cloud AI tasks, history and attachments, provider and credential settings, MCP, an on-device Linux terminal and jobs, files, a code IDE, Git, a browser, built-in Office viewing and basic editing, and core Notes workflows. The network workbench includes Wi-Fi, LAN discovery, DNS, Ping, TCP, HTTPS, speed tests, monitoring and redacted reports. Alpha21 adds offline PCAP/PCAPNG analysis, saved Wi-Fi coverage points with an optional floorplan, and scheduled Agent tasks in separate conversations. Exact-time scheduling requires system access; flexible timing is an explicit choice. Android does not provide local-model inference. System/configured cloud voice, read-only CAD/3D previews and the signed Skill Hub client are included for continued device validation; optional components, compatible packages and configuration determine availability. Professional editing can use Android apps or a project Linux graphical session; lightweight editing stays in Floe. See the release notes for tested devices and limits. Alpha48 |
For your first iOS / iPadOS task: install → connect a model → create a task → open the result. Core Notes, file organization and Canvas work without an AI provider; AI features use your configured provider or a local model supported by your device. On Android: install → add your cloud provider key → start chatting; Basic Notes editing works without a provider; AI actions use your cloud configuration. Office files, the file workspace, the Linux terminal, the code IDE and the network workbench are already in the alpha.
Installation steps · Model setup · Sources and signing
The iOS setup guide offers four recommendations to prefill choices for models, search, voice and workspaces, while keeping every section editable. Continue setup while voice packs, models or environments download, then check progress later. Apple Intelligence is off by default for new users.
iOS 1.8.2 (322) integrates this round of predevelopment work and is available through internal TestFlight. Apple processing is valid, the build is unexpired, and Floe QA availability is verified. See the integration record and build notes. Interface acceptance covers menus, pages opening, controls and the agreed layouts; comprehensive functional and stability qualification was not repeated.
The features below describe Floe core workflows. Availability varies by platform and release; see the installation notes above and the Android release for the current Android alpha.
| Workflow | What you can do | Guide |
|---|---|---|
| AI tasks | Continue a task with your material, tool actions and resulting files together. | Tasks & workspaces |
| On-device Linux | Run agent code in a persistent, task-owned Linux environment on your device: shell, Python, Node and apt packages, background jobs and local web previews. Requires the verified image download; packages must support the environment's architecture. | Local terminal & Linux |
| On-device AI | Run inference on your device with supported local models — the system model or downloaded models (Beta). Availability depends on your device and model status; local models share memory with Linux. | Model setup |
| Notes | Import PDFs and images, search, annotate with Pencil and ask about documents. | Notes |
| Office | Create, edit and save DOCX, XLSX and PPTX. Check saved results with complex layouts. | Documents, sheets & slides |
| Canvas & media | Organize material on a canvas and use focused image, video and audio workbenches. | Canvas & media |
| Drawings & 3D | On iOS/iPadOS, edit 2D drawings and create native 3D models in one workbench — keep refining them with the assistant, apply materials and present or export the result. Operations vary by format. | Native 3D editor · 2D drawings |
| Code & remote | Edit code, track Git changes and work with authorized remote hosts. | Terminal & ports · Remote connections |
| Voice | Dictate editable drafts, hold voice conversations and have final answers read aloud with system, enhanced on-device or configured online voices. Android includes system/configured cloud voice paths; provider and device behavior remains under validation, and Android has no App-managed local voice model. | Voice input & read-aloud |
| Skills & Skill Hub | Install reviewed skills with declared dependencies and version managemen |