instavm/clickclickclick
A framework to enable autonomous android and computer use using any LLM (local or remote)
Implements a two-model architecture with separate "planner" and "finder" LLMs—the planner decomposes tasks into steps while the finder locates UI elements via vision, enabling reliable autonomous interaction across Android and macOS. Supports both cloud APIs (OpenAI, Gemini) and local models via Ollama, with configurable image quality for latency-performance tradeoffs. Exposes functionality through CLI, REST API, and Python SDK, integrating with ADB for Android device control.
670 stars. No commits in the last 6 months.
Stars
670
Forks
83
Language
Python
License
MIT
Category
Last pushed
Oct 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/instavm/clickclickclick"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GoogleCloudPlatform/agent-starter-pack
Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in...
quantalogic/quantalogic
Quantalogic ReAct Agent - Coding Agent Framework - Gives a ⭐️ if you like the project
amd/gaia
Build AI agents for your PC
exospherehost/runtime
Runtime for building and managing AI agents and Workflows. Easy to learn, fast to build, High...
eggai-tech/EggAI
Async-first meta framework for building enterprise-grade multi-agent systems.