Verified project record

lsdefine/GenericAgent

A minimal (~3K lines) autonomous agent framework that executes system-level tasks and grows its own skill tree from execution history using 9 atomic tools. It operates within a <30K context window to reduce token consumption while providing control over local terminals, browsers, and mobile devices.

Project overview

Project type: AI Agent · Workflow · Infrastructure
Use cases: Documents & Office · Automation
Deployment: Refer to project documentation
License: MIT

Best for

Developers and AI engineers looking for a self-hosted agent framework that operates with a <30K context window and accumulates reusable skills from execution history.

Key capabilities

A ~100-line core loop that enables an LLM to perceive environment state, reason about tasks, execute tools, and write experience to memory.
Automatically crystallizes each successful task execution into a reusable Skill, growing a personal skill tree from seed code without manual intervention.
Provides 9 atomic tools including code_run, file_read, file_write, file_patch, web_scan, web_execute_js, ask_user, and memory update functions for foundational interaction.
Features a 5-layer (L0-L4) hierarchical memory system including Meta Rules, Insight Index, Global Facts, Task Skills, and Session Archive for efficient routing and recall.
Injects into a real browser via a local WebSocket server and Chrome extension to preserve login sessions, cookies, and normal browser fingerprints, passing bot detection tests.
Grants system-level control over a local computer covering terminal, filesystem, keyboard/mouse input, screen vision, and mobile devices (ADB).
Dynamically installs Python packages, writes scripts, calls external APIs, or controls hardware at runtime, crystallizing temporary abilities into permanent tools.
Multi-worker cooperative Goal mode using BBS-coordinated master/workers running long-horizon objectives in parallel.

Limitations and risks

Terminal UI rendering on Windows can be flaky depending on the terminal and font used.
The framework is incompatible with Python 3.14 due to dependencies such as pywebview.
Pre-installed SOPs are written in Chinese, which requires a manual translation prompt for English use.
Providing direct system-level control including arbitrary code execution introduces security risks if misused.

Getting started

Clone the repository, install with uv using the one-line installer, add your LLM API key, and run the framework. The setup has minimal dependencies.

Evidence and sources

GitHub project description: Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
README: **A Minimal, Self-Evolving Autonomous Agent Framework** *~3K lines of seed code · 9 atomic tools · ~100-line Agent Loop*
README: 💰 **Token Efficient** | <30K context window — a fraction of the 200K–1M other agents consume. Less noise, fewer hallucinations, higher success rate, lower cost.
README: - **2026-01-16** — GenericAgent **V1.0** public release.
README: Perceive environment state → Task reasoning → Execute tools → Write experience to memory → Loop

Reviewed at: 2026-07-18T00:01:25Z