evolver
AI agent self-evolution engine based on the GEP protocol, supporting genes, capsules, and events.
- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 8.7k
- Source
- mcp-github
- Repository
- github.com/EvoMap/evolver
Overview
Evolver is a self-evolving AI agent engine based on the GEP protocol. It encodes agent experiences into genes and capsules, rather than temporary prompts or skill documents. This approach allows Evolver to transform transient prompt adjustments into auditable, reusable evolutionary assets. Ideal for developers aiming to enhance AI agent performance and achieve continuous evolution. Can be installed via npm and run within any git-initialized repository.
Capabilities
- ▪Self-evolution based on the GEP protocol
- ▪Experience encoding using genes and capsules
- ▪Auditable evolution process
- ▪Support for multiple AI agents
Use cases
Setup
npm install -g @evomap/evolver
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with Evolver?
After installation, run the `evolver` command in any git-initialized project directory.
Is Evolver open source?
Yes, Evolver is currently source-available.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.