evolver — What is it?

EvoMap/evolver is a GEP-powered self-evolving engine for AI agents, addressing the need for auditable, reusable evolution assets in AI development.

⭐ 7,605 Stars 🍴 776 Forks JavaScript GPL-3.0 Author: EvoMap
Source: README View on GitHub →

Why it matters

This project is gaining attention due to its innovative approach to AI agent evolution using Genes, Capsules, and Events, offering a unique solution for creating auditable and reusable evolution assets. Its focus on Genes as a compact representation for agent experience stands out, as evidenced by its performance improvements in scientific code-solving scenarios. The transition to source-available while maintaining a commitment to users also adds to its appeal.

Source: README, Research section

Core Features

Genome Evolution Protocol (GEP)

A protocol for encoding agent experience as Genes and Capsules, enabling auditable and reusable evolution assets. It uses Genes as a compact representation for agent experience, leading to improved performance and robustness.

Source: README, Research section
CLI Quick Start

A simple and straightforward command-line interface for running evolutions, reviewing changes, and setting up continuous loops. It supports integration with various agent runtimes.

Source: README, CLI Quick Start section
Integration with Agent Runtimes

Support for integration with major agent runtimes like Cursor, Claude Code, Codex, Kiro, OpenClaw, and opencode, allowing for seamless use within existing workflows.

Source: README, Wire up your agent runtime section

Architecture

The architecture is modular, with clear separation of concerns. It includes an adapter layer for different agent runtimes, a core engine for evolution, and a data storage layer for memory and logs. The use of Genes and Capsules as the core data structure for evolution is a key architectural decision.

Source: Code tree, package.json

Project Knowledge Graph

Knowledge graph: project (center) + core features (inner hexagons) + key dependencies (outer chips) dotenv Genome Evolution Protocol (GEP)Genome Evolution Pr… CLI Quick Start Integration with Agent RuntimesIntegration with Ag… evolver Project Core feature Key dependency

Center: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.

Tech Stack

LanguageJavaScriptFrameworkNode.js
dotenv
Not enough information.
Source: package.json, Code tree

Quick Start

```bash npm install -g @evomap/evolver # Verify the CLI is on your PATH evolver --help # Run from inside any git repo evolver # Review mode evolver --review # Continuous loop evolver --loop ```
Source: README, CLI Quick Start section

Use Cases

EvoMap/evolver is suitable for developers and technical decision-makers working on AI agent development. It is useful in scenarios where AI agents need to evolve and adapt based on experience, such as in scientific code-solving, automation, and meta-learning.

Source: README

Strengths & Limitations

Strengths

  • Strength 1: Innovative approach to AI agent evolution using Genes and Capsules.
  • Strength 2: Strong focus on auditable and reusable evolution assets.
  • Strength 3: Easy to integrate with major agent runtimes.

Limitations

  • Limitation 1: Transition to source-available may limit full access to the codebase.
  • Limitation 2: Limited information on deployment and runtime infrastructure.
Source: README, Code tree, package.json

Latest Release

v1.80.7 (2026-05-09): Bug fixes and UX improvements.

Source: GitHub Releases

Verdict

EvoMap/evolver is a promising project for those interested in AI agent evolution and meta-learning. Its innovative approach to encoding and reusing agent experience through Genes and Capsules offers a unique solution for AI development. Its ease of integration with major agent runtimes makes it a valuable tool for developers working in this field.

Transparency Notice
This page is auto-generated by AI (a large language model) from the following public materials: GitHub README, code tree, dependency files and release notes. Analyzed at: 2026-05-22 21:33. Quality score: 85/100.

Data sources: README, GitHub API, dependency files