# EvoMap/evolver

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

Repository: https://github.com/EvoMap/evolver
Canonical: https://ross.abutalabs.com/products/evolver
Homepage: https://evomap.ai
Language: JavaScript
License: GPL-3.0
License Family: copyleft
Topics: a2a, agent-evolution, agent-framework, agent-protocol, ai-agent, auditable-ai, autonomous-agent, cli, evomap, gep, llm-agent, mcp, memory-system, nodejs, prompt-engineering, prompt-governance, self-evolution, self-evolving, skill-library, skills
Last push: 2026-08-25T17:53:18+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 15
- inputs: {"age_days": 213, "days_push": 8, "days_rel": 13, "gap_med": 0.0, "n_releases_24m": 103}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9007, forks 841 (observed 2026-08-28T04:10:26.744769+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, prompt-engineering, mcp, cli
- domain: large-language-models, developer-tools
- platform: cli, cross-platform
- tags: self-evolving-agents, gep, auditable-ai, skill-library, agent-protocol, a2a, prompt-governance, memory-system, source-available-transition, ai-agents, automation, nodejs

## Member repositories
- EvoMap/evolver (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:26.744769+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:24:21.146951+00:00, confidence not recorded.
  - readme: https://github.com/EvoMap/evolver (fetched 2026-08-28T04:10:26.744769+00:00, sha cafbc18b0fe2)
  - homepage: https://evomap.ai (fetched 2026-08-29T08:24:38.524959+00:00, sha c3bc3d02b0cb)
  - site_page: https://evomap.ai/dev/docs (fetched 2026-08-29T08:24:38.537698+00:00, sha b2a8238c86d1)
  - site_page: https://evomap.ai/pricing (fetched 2026-08-29T08:24:38.533935+00:00, sha ecd1e39cc145)
  - site_page: https://evomap.ai/integrations (fetched 2026-08-29T08:24:38.535947+00:00, sha 10a17b844ee2)
- Data as of 2026-08-30T08:39:29.467469+00:00.