evolver
The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
Source#
- Repository: EvoMap/evolver
- Last source update: 2026-04-26
- Last verified: 2026-04-26
Tags#
Integration notes#
Repository is focused on tool/server interoperability; wrap in bounded worker contracts for production use.
worker.md example#
Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.
---
id: evolver-repo-derived-worker
name: evolver Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/evolver/
source_repository: https://github.com/EvoMap/evolver
repository_default_branch: main
repository_language: JavaScript
repository_license: GPL-3.0
repository_updated_at: 2026-04-26
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-04-26
tags:
- a2a
- agent-evolution
- agent-framework
- agent-protocol
- ai-agent
- auditable-ai
---
# evolver Repo-Derived Worker
## Repo-derived summary
- Registry summary: The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
- Repository description: The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
- Stars (snapshot): 6,911
- Primary language: JavaScript
- Worker mode classification: agent-orchestration-worker
## Extracted from
- https://github.com/EvoMap/evolver
- https://github.com/EvoMap/evolver/blob/main/README.md
- https://img.shields.io/github/stars/EvoMap/evolver?style=social
- https://img.shields.io/github/last-commit/EvoMap/evolver
- https://img.shields.io/github/issues/EvoMap/evolver
## Evidence notes (from repository text)
- README summary paragraph: **https://evomap.ai** | https://evomap.ai/wiki | [Chinese / 中文文档](README.zh-CN.md) | [Japanese / 日本語ドキュメント](README.ja-JP.md) | [Korean / 한국어 문서](README.ko-KR.md) | https://github.com/EvoMap/evolver | https://github.com/EvoMap/evolver/releases
- - **What it is**: A https://evomap.ai/wiki-powered self-evolution engine for AI agents.
- | **CLI Quick Start** | You just want to use Evolver to evolve an agent / project. 99% of readers. | `evolver` | [below](#cli-quick-start) |
- 2. It scans `./memory/` (creates it if missing) for logs and signals.
- 4. It prints a **GEP prompt** to stdout -- that's the artifact. Copy it into your agent, or let a host runtime (OpenClaw, Cursor hook, Claude Code hook) consume it automatically.
- 5. It writes an `EvolutionEvent` into `./memory/` for audit.
## Installation hints found in README
- `npm install @evomap/evolver` or clone this repo; nothing in your current workflow breaks.`
- `npm install -g @evomap/evolver`, then run `evolver` in any git repo.`
- `npm install -g @evomap/evolver`
- `npm install location):`
## worker.md contract (derived starter)
Purpose: Execute one orchestrated agent task as a bounded worker step.
### Input schema
```json
{
"type": "object",
"additionalProperties": false,
"required": [
"run_id",
"task",
"context"
],
"properties": {
"run_id": {
"type": "string"
},
"task": {
"type": "string"
},
"context": {
"type": "object"
}
}
}
```
### Output schema
```json
{
"type": "object",
"additionalProperties": false,
"required": [
"run_id",
"status",
"result"
],
"properties": {
"run_id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"ok",
"retryable_error",
"invalid_request",
"invalid_output"
]
},
"result": {
"type": "object"
}
}
}
```
### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: run_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use
## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.
How to use#
- Save this as a worker spec file (for example:
evolver-my-task.worker.md). - Replace the input/output schemas and purpose with your real bounded task.
- Enforce schema validation + timeout + retry policy in your runtime before production use.
Citation#
Reference URL: https://worker.md/registry/evolver/
Source URL: https://github.com/EvoMap/evolver