lsdefine/GenericAgent

Health v2 · maintenance only

Adoption not part of the score

14042 stars · 1634 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

framework · maturity active

agent-framework workflow-automation computer-vision llm-inference artificial-intelligence large-language-models python cross-platform cli self-evolving skill-tree autonomous-agent computer-control browser-automation memory-system lightweight ai-agents automation desktop

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lsdefine/GenericAgent")