Awesome Agent Evolution
A curated list of projects, papers, and benchmarks on AI agent self-evolution, memory systems, multi-agent architectures, and self-improvement, organized into a taxonomy with short descriptions of each entry.
This is an awesome-list style directory covering how AI agents evolve and improve themselves. Its sections cover agent evolution and self-improvement frameworks, memory systems, agent-to-agent protocols, agent development platforms, agent coding and software-engineering tools, multi-agent frameworks, prompt and behavior optimization, agent safety and guardrails, embodied AI, key research papers, benchmarks and evaluation, and community resources.
Each entry gives a one-line description of the linked project and its maintaining organization or author, covering frameworks such as Eliza, Agent Zero, SuperAGI, and OpenEvolve alongside continual-learning infrastructure and self-improving multi-agent desktop applications.
The list is maintained as a companion resource to a related agent-evolution project and organized around an explicit taxonomy of the space rather than a flat alphabetical list.