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.
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.
deepclaude is a backend adapter for the Claude Code CLI that redirects its autonomous agent loop to cost-effective models like DeepSeek V4 Pro. It preserves core features such as file editing, terminal execution, and subagent spawning while reducing costs by 17x through DeepSeek's automatic context caching. The tool supports mid-session backend switching via slash commands, remote control via web browsers, and real-time cost tracking, offering a high-performance yet affordable extension to the autonomous coding ecosystem.
Dexter is an autonomous financial research agent that thinks, plans, and learns. It decomposes complex queries into structured tasks, executes them using real-time market data, and employs self-reflection to validate results. Built with Bun and supporting multiple LLMs, it provides data-backed financial insights with integrated safety features.