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.

skills.sh installs: 897
GitHub stars: 14.4K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Evolving AI Agents with A-Evolve

Overview

A-Evolve is universal infrastructure for evolving any AI agent across any domain using any evolution algorithm with zero manual engineering. It represents all evolvable agent state as files (prompts, skills, memory, tools), runs iterative solve-observe-evolve cycles against benchmarks, and uses LLM-driven mutation to improve agent performance automatically.

Benchmark results (Claude Opus 4.6):

MCP-Atlas: 79.4% (#1)
SWE-bench Verified: 76.8% (~#5)
Terminal-Bench 2.0: 76.5% (~#7)
SkillsBench: 34.9% (#2)

When to Use A-Evolve

Use A-Evolve when:

Optimizing agent prompts, skills, or memory against a measurable benchmark
Building self-improving agents with automated gating and rollback
Evolving domain-specific tool usage and procedures through LLM-driven mutation
Running iterative solve-observe-evolve loops to maximize agent performance
Needing reproducible, git-versioned evolution history for every change

Key differentiator: Other frameworks build agents; A-Evolve optimizes them. It sits on top of any agent framework and makes it better through automated evolution.

SKILL.md on GitHub