Google PageRank for AI agents. 25,000+ tools indexed.

Autofish MCP Server

felinics/Autofish

Score: 56.2 Rank #8415 AI Tool
[![AgentRank](https://agentrank-ai.com/api/v1/badge/felinics--Autofish)](https://agentrank-ai.com/tool/felinics--Autofish/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of felinics/Autofish? Claim this listing →

An AI Agent tool to automate Android devices reliably

Add AgentRank to Claude Code Discover and compare tools like felinics/Autofish — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

felinics/Autofish is a Rust agent tool licensed under Apache-2.0. An AI Agent tool to automate Android devices reliably Topics: ai-agent, android, android-automation, llm, mobile-automation.

Ranked #8415 out of 24846 indexed tools.

Ecosystem

Rust Apache-2.0
ai-agentandroidandroid-automationllmmobile-automation

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 119

119 stars → growing community

Freshness 25% 2mo ago

Last commit 2mo ago → moderate activity

Issue Health 25% 50%

1/2 issues closed → decent issue management

Contributors 10% 2

2 contributors → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 10
Description Good
License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 74 days ago — a recent commit would boost your freshness score

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

AgentRank score for felinics/Autofish
[![AgentRank](https://agentrank-ai.com/api/v1/badge/felinics--Autofish)](https://agentrank-ai.com/tool/felinics--Autofish/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/felinics--Autofish/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/felinics--Autofish" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="felinics/Autofish"></script>

Matched Queries

"agent tool"

From the README

# Autofish

English | [中文](./README_ZH.md)

**Android control infrastructure for agents and multi-agent systems.**

Autofish gives any agent a stable, explicit, and observable Android execution layer: inspect the screen, act through stable refs instead of brittle coordinates, verify outcomes after every step, and recover with local execution memory.

```text
human → agent → autofish → Android device
         ↑                       |
         └── observe / verify ───┘
```

## How It Works

Autofish has two components:

**Android Service** — A foreground service running on the device, exposing an HTTP API. It handles screenshots, UI tree inspection, tap/swipe/text input execution, and on-screen overlay annotations.

**CLI (`af`)** — A Rust binary that talks to the service over HTTP. It provides the command interface, manages local tool memory (SQLite), and handles artifact storage. Distributed via npm (`@memohjs/af`).

## Install and Connect

Install Autofish from npm:

```bash
npm i -g
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.