# lsdefine/GenericAgent

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

Repository: https://github.com/lsdefine/GenericAgent
Canonical: https://ross.abutalabs.com/products/genericagent
Homepage: https://github.com/lsdefine/GenericAgent
Language: Python
License: MIT
License Family: permissive
Topics: ai-agent, automation, autonomous-agent, browser-automation, claude, computer-control, desktop-automation, gemini, lightweight, llm-agent, memory-system, python, self-evolving, skill-tree, task-automation
Last push: 2026-08-25T10:29:05+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 87, longevity 16
- inputs: {"age_days": 229, "days_push": 8, "days_rel": 9, "gap_med": 38, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14042, forks 1634 (observed 2026-08-28T04:11:05.372040+00:00)

## What it is
GenericAgent is a minimal self-evolving autonomous agent framework (~3K lines of seed code) that gives any LLM system-level control over a local computer via 9 atomic tools and a ~100-line agent loop. It automatically crystallizes solved tasks into reusable skills, growing a personal skill tree with reduced token consumption.

## Use cases
- automate desktop tasks with an llm agent
- control browser and terminal via natural language
- build a self-evolving agent that learns new skills
- automate keyboard mouse and screen interactions
- control android devices through adb from an agent
- reduce token costs for autonomous agent workflows

## When to choose
- you want a lightweight, minimal agent framework you can read and extend
- you need full local system control (browser, terminal, filesystem, input, screen vision)
- you want skills to accumulate automatically from repeated tasks
- you prefer token-efficient autonomous execution

## When to avoid
- you need a heavily engineered, enterprise-grade multi-agent orchestration platform
- you require sandboxed security and cannot grant an agent full system access
- you only need simple scripted automation without an LLM

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, workflow-automation, computer-vision, llm-inference
- domain: artificial-intelligence, large-language-models
- platform: python, cross-platform, cli
- tags: self-evolving, skill-tree, autonomous-agent, computer-control, browser-automation, memory-system, lightweight, ai-agents, automation, desktop

## Member repositories
- lsdefine/GenericAgent (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:05.372040+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:12:51.470015+00:00, confidence not recorded.
  - readme: https://github.com/lsdefine/GenericAgent (fetched 2026-08-28T04:11:05.372040+00:00, sha c3a72e1bf8e1)
  - homepage: https://github.com/lsdefine/GenericAgent (fetched 2026-08-29T08:06:42.719052+00:00, sha 16a1466927e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.