#8686th of 118 in Agent frameworks and SDKs
evolver
CLI that turns agent logs into reusable Gene and Capsule evolution prompts
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 8.7k
- License
- GPL-3.0
- Last commit
- Sep 2026
- Last release
- Nov 2026
- Language
- JavaScript
6,185 on 21 Apr 20268,740 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Evolver is a Node.js CLI that scans a project's memory/ logs, selects a matching Gene or Capsule from a local asset store, and prints a protocol-bound GEP prompt to stdout. It records an EvolutionEvent for audit and does not edit source code itself. Hooks exist for Cursor, Claude Code, Codex, Kiro and opencode; connecting to the EvoMap Hub is optional.
Who it is for: Teams maintaining agent prompts and logs who want auditable, reusable fixes
Strengths
- Core features run fully offline; the EvoMap Hub connection is optional
- setup-hooks wires into Cursor, Claude Code, Codex, Kiro and opencode
- Every cycle writes an auditable EvolutionEvent, with a --review confirmation mode
- Strategy presets (balanced, innovate, harden, repair-only) set the intent mix
Weaknesses
- Only generates prompts; it does not patch code or run changes itself
- Requires a git repository; fails in non-git directories
- Maintainers say future releases move from GPL-3.0 to source-available
- Loop mode output is not picked up by a live host agent session
What it needs
- no GPU
- Needs Node.js >= 18, Git
Quick answers
Is evolver open source?
Yes. Its code is on GitHub under the GPL-3.0 license.
Does evolver need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |