Evolving Ai Agents

A-Evolve treats your AI agent's entire state as files (prompts, skills, memory, tools) and evolves them automatically through solve-observe-evolve cycles against benchmarks. It's universal infrastructure that works with any agent, any domain, and any evolution algorithm without manual engineering. The benchmark results are legitimately impressive: 79.4% on MCP-Atlas (first place), 76.8% on SWE-bench Verified, and solid scores on Terminal-Bench and SkillsBench. This is the kind of tool you'd reach for when you want to systematically improve agent performance rather than tweaking prompts by hand. The approach is clever because it leverages LLM-driven mutations, so the agents evolve themselves based on what works.

Install to Claude Code

npx -y skills add orchestra-research/ai-research-skills --skill evolving-ai-agents --agent claude-code