EvoMap/evolver

Health v2 · maintenance only

Adoption not part of the score

9007 stars · 841 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Evolver is a Node.js-based self-evolving engine for AI agents built on the GEP (Gene Evolution Protocol), letting agents turn experience into reusable, auditable assets such as Genes, Capsules, and Events. It ships as an npm package and CLI, integrates with MCP, A2A, and major agent frameworks, and connects to the EvoMap experience-sharing network.

Use cases

• make my AI agent improve itself from past experience
• build a skill library my agents can reuse and share
• audit and govern how agent prompts and skills evolve
• connect MCP tools as reusable evolution assets across agents
• share learned agent capabilities across a team or ecosystem
• run self-evolving LLM agents from the command line

When to choose

• you want auditable, versioned evolution of agent skills and prompts
• you use Node.js and want npm/CLI integration with MCP or A2A protocols
• you want agents to inherit learned capabilities from a shared network

When to avoid

• you need a permissively licensed dependency going forward - future releases are moving to source-available
• you want a fully offline solution without any platform/network dependency
• you need a Python-first agent stack with no JavaScript runtime

Facets

framework · maturity active

agent-framework llm-inference prompt-engineering mcp cli large-language-models developer-tools cli cross-platform self-evolving-agents gep auditable-ai skill-library agent-protocol a2a prompt-governance memory-system source-available-transition ai-agents automation nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="EvoMap/evolver")