#autonomous-agent

GenericAgent is a minimalist, self-evolving autonomous agent framework with only ~3K lines of core code. Utilizing 9 atomic tools and a ~100-line Agent Loop, it grants any LLM system-level control over local computers, covering browsers, terminals, filesystems, keyboard/mouse input, screen vision, and mobile devices. Its design philosophy is to evolve skills rather than pre-loading them, automatically crystallizing execution paths into reusable skills after each task, fostering a personal skill tree that grows with use, all while being highly token-efficient.

Evolver, the core engine of the EvoMap ecosystem, is a GEP-protocol-powered self-evolution engine for AI agents. It transforms ad-hoc prompt adjustments into auditable and reusable evolution assets like Genes and Capsules. By scanning runtime logs and identifying error patterns, Evolver selects suitable assets and generates standardized GEP prompts to guide the AI agent's next evolutionary step. It supports various strategy presets and integrates with major agent runtimes like OpenClaw and Cursor, enabling automated agent self-repair and capability enhancement.