GenericAgent

GenericAgent is an autonomous agent framework that grows a personal skill tree from seed code and executes tasks.

GenericAgent is a minimal, self-evolving autonomous agent framework built on approximately 3K lines of seed code and a 100-line agent loop. It uses 9 atomic tools to grant large language models direct system-level control over a local computer, including browsers, terminals, filesystems, keyboard and mouse input, screen vision, and mobile devices via ADB. Every time the agent solves a new task, it automatically crystallizes the execution path into a reusable skill, building a personal skill tree over time. It supports major models such as Claude, Gemini, Kimi, and MiniMax, and operates across multiple platforms. The framework is designed for users who want an agent that builds its own environment and capabilities dynamically through execution rather than preloaded packages.

GenericAgent at a glance

Best for: Software engineer
Runs on: macOS, Windows, Linux, Web, Telegram, Discord, CLI
Pricing: Free
Released: January 2026
Category: AI agent tool
Website: github.com/lsdefine/GenericAgent

Key features

Self-evolving skill tree generation
Minimal architecture with 3K lines of core code
Direct system control using 9 atomic tools
Real browser session integration and automation
Mobile device control through ADB
Layered memory system for task persistence
Cross-platform adaptation and execution

Use it for

Automating web exploration and scraping
Executing quantitative stock screening
Managing expenses and mobile app actions
Sending bulk messages across chat clients
Ordering food delivery through apps

Alternatives to GenericAgent

OmniAgent — It evolves skills in real-time and dynamically hardens security during task execution.
MyAgent — It features built-in permission controls, long-term memory, and skill self-evolution.
VoltAgent — Offers open-source flexibility with built-in supervisor agent orchestration and RAG.
II-Agent — It provides a fully open-source, transparent, and auditable agent foundation.
AGiXT — Builds autonomous agents with integrated memory and web capabilities.
Agent Executor — Declarative runtime for scaling stateful agent workloads with isolation.
Rakazo — Complete ownership of data, models, and execution environment.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Adyen — Share AI agent resources across coding tools and repositories easily.
SkillClaw — Automatically evolves and unifies agent skills across devices and team members.
Mobile-Agent — Automates cross-platform GUI tasks via planning and multimodal memory.
Airtop — Compiles plain English into reliable, self-healing, efficient agents.

All GenericAgent alternatives