What makes agent-android notable?

1.1K downloads. Trust evidence available

How should agent-android be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

agent-android

agent-android for AI agents

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

0.1.6

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 0.1.6release · observed Apr 16, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1715h06na20d964bkr1mcyrz184z5pg:agent-android

Install using `clawhub skill install s1715h06na20d964bkr1mcyrz184z5pg:agent-android` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/crazytigerman/agent-android before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-crazytigerman-agent-android/snapshot"

Documentation

CLAWHUB

62,075 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: agent-android
description: Control Android over LAN without USB, ADB, or root.
metadata: {"openclaw":{"homepage":"https://github.com/aivanelabs/ai-rpa","requires":{"bins":["agent-android"]},"install":[{"id":"agent-android-uv","kind":"uv","package":"aivane-agent-android","bins":["agent-android"],"label":"Install agent-android CLI (uv)"}]}}
---

# Android REPL

Use this skill to drive an Android device through the public `agent-android` beta surface published in the `aivanelabs/ai-rpa` repo.

Runtime prerequisites:

- `agent-android` is available on `PATH`
- if it is missing, install the CLI with `uv tool install aivane-agent-android`; then run `uv tool update-shell` if the command is still not found
- the user has provided a trusted device URL such as `http://<device-ip>:8080`

The public path is local-first:

- the phone hosts the lightweight HTTP service locally
- the desktop connects directly to `http://<device-ip>:8080`
- UI reads, taps, inputs, and screenshots stay on the phone and controlling machine
- the current tradeoff is LAN-only control; an optional server-side or relay path may arrive later

If an `agent-android` command suddenly stops working, first check whether the AIVane app or its local API service has exited on the phone.

## Safety Boundaries

- Connect only to a device URL explicitly provided by the user.
- Do not scan local networks or guess device IP addresses.
- Treat UI trees and screenshots as sensitive because they may contain private app content.
- Save screenshots or raw UI dumps only when the user explicitly asks for a file output.
- Ask for confirmation before operating sensitive apps, private content, account settings, or irreversible actions.
- Do not expose the phone-side service on a public network.

## Core Workflow

Every Android control task should follow the same short loop:

1. Confirm connectivity with `/health`
2. Discover the target app with `apps` if needed
3. Launch one app
4. Inspect the current UI tree
5. Perform one action
6. Inspect again

Keep the loop short. Prefer inspect -> act -> inspect over long speculative command chains.

## Quick Start

Start the REPL with the user-provided device URL:

- `agent-android --repl --url http://<device-ip>:8080`

Built-in help:

- `agent-android --help`
- In the REPL: `h`

## Essential CLI Commands

Use the one-off CLI when you already know the exact action you want.

Connectivity:

- `agent-android --health --url http://<device-ip>:8080`

Discovery:

- `agent-android --apps --url http://<device-ip>:8080`
- `agent-android --list --url http://<device-ip>:8080`
- `agent-android --id com.example:id/search --url http://<device-ip>:8080`
- `agent-android --text Search --url http://<device-ip>:8080`
- `agent-android --inputs --url http://<device-ip>:8080`
- `agent-android --refId 7 --url http://<device-ip>:8080`
- `agent-android --xpath 7 --url http://<device-ip>:8080`
- `agent-android --get-attr 7 text --url http://<device-ip

_meta.json

{
  "ownerId": "kn77cfv5yzn6q2zqaewdexqsth84z5tf",
  "slug": "agent-android",
  "version": "0.1.6",
  "publishedAt": 1776315481598
}

references/smoke-flow.md

# Android REPL Smoke Flow

Use this checklist when validating a fresh setup.

## Preconditions

- Android REPL app installed
- API service running
- controlling machine on the same LAN
- `agent-android` available on `PATH`

## Checklist

1. Save the device URL:

```text
set url http://<device-ip>:8080
```

2. Check service health:

```bash
curl http://<device-ip>:8080/health
```

3. List launcher apps:

```bash
agent-android --apps --url http://<device-ip>:8080
```

4. Launch the target app.
5. List the current UI tree.
6. Perform one tap.
7. Perform one text input if relevant.
8. Navigate back.

## Success Criteria

- the device responds
- launcher apps are visible
- launch succeeds
- the UI tree refreshes after actions
- the user can complete at least one inspect -> act -> inspect loop

skill-card.md

## Description:

Control Android over LAN without USB, ADB, or root.

This skill is ready for commercial/non-commercial use.

## Publisher:

[crazytigerman](https://clawhub.ai/user/crazytigerman)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and operators use this skill to connect to a trusted Android device on the same LAN, inspect apps and UI state, and drive step-by-step tap, input, navigation, and screenshot workflows without USB, ADB, or root.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can read and control an Android device over unauthenticated plaintext LAN HTTP.

Mitigation: Use only a trusted device URL provided by the user, keep the phone service off public or shared Wi-Fi, and prefer an isolated trusted network or encrypted tunnel.

Risk: UI trees and screenshots can expose private app content.

Mitigation: Use a test device or non-sensitive apps when possible, ask for confirmation before sensitive or irreversible actions, and save screenshots or raw UI dumps only when explicitly requested.

Risk: The uv-installed dependency is not version-pinned in the skill metadata.

Mitigation: Review the upstream package before installation and confirm the installed package version is acceptable for the deployment.

## Reference(s):

- [Project homepage](https://github.com/aivanelabs/ai-rpa)
- [Smoke checklist](https://github.com/aivanelabs/ai-rpa/blob/main/skills/agent-android/references/smoke-flow.md)
- [Quickstart](https://github.com/aivanelabs/ai-rpa/blob/main/docs/quickstart.md)
- [Install guide](https://github.com/aivanelabs/ai-rpa/blob/main/docs/install-agent-android.md)
- [Public protocol](https://github.com/aivanelabs/ai-rpa/blob/main/docs/protocol-v1.md)
- [Known beta limits](https://github.com/aivanelabs/ai-rpa/blob/main/docs/known-limitations.md)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown with inline shell commands]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include user-approved Android control commands, trusted device URL placeholders, and screenshot file paths when explicitly requested.]

## Skill Version(s):

0.1.6 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

agents/openai.yaml

interface:
  display_name: "agent-android"
  short_description: "agent-android for AI agents"
  default_prompt: "Use $agent-android from the aivanelabs/ai-rpa repo to connect to an AIVane device over LAN, inspect launcher apps and UI state, then control the phone step by step."

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.