Skip to content
AgentRadar
GenericAgent

GenericAgent

Self-evolving agent: grows skill tree from 3

Productivity Agents Open Source

Last Updated

2026-06-16

GitHub Stars

12,889

Last Updated

2026-07

About GenericAgent

A Minimal, Self-Evolving Autonomous Agent Framework ~3K lines of seed code · 9 atomic tools · ~100-line Agent Loop GenericAgent is a minimal, self-evolving autonomous agent framework. Its core is just ~3K lines of code. Through 9 atomic tools + a ~100-line Agent Loop, it grants any LLM system-level control over a local computer — covering browser, terminal, filesystem, keyboard/mouse input, screen vision, and mobile devices (ADB). Every time GenericAgent solves a new task, it automatically crystallizes the execution path into a reusable Skill. The longer you use it, the more skills accumulate — forming a personal skill tree grown entirely from 3K lines of seed code. - Demo Showcase

Features

Linux / macOS

Detailed Ratings

Ease of Use
6.8
Value for Money
7.4
Features
7.0
Support
6.6
Performance
7.2
Overall Rating
7.1 /10

Pros & Cons

Pros

  • Active community with 12.9k GitHub stars
  • Linux / macOS

Use Cases

Workflow automationTask managementSchedulingIntegrations

Who Is It For?

Teams and individuals looking for productivity and workflow automation who value open-source flexibility and control.

#ai-agent#automation#autonomous-agent#browser-automation#claude#genericagent

Frequently Asked Questions

What is GenericAgent?

**A Minimal, Self-Evolving Autonomous Agent Framework**

How much does GenericAgent cost?

GenericAgent is open-source and free to self-host. See https://github.com/lsdefine/GenericAgent for installation instructions.

Is GenericAgent open source?

Yes — GenericAgent is open source with 12.9k stars. The source code is on GitHub at https://github.com/lsdefine/GenericAgent.

Who should use GenericAgent?

Teams and individuals looking for productivity and workflow automation who value open-source flexibility and control.

Related Agents

Links & Resources

AR Reviewed by AgentRadar · Reviewed on · How we rate

Profiles are AI-assisted from public information — not independently hands-on tested.