No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by EXboys · Codex Skill · ★ 648
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is evotown safe to install? View the security audit →
Evotown — Evolution Testing Platform Puts evolution engines in a controlled environment for evolution effect validation — OpenClaw-style stacks, Hermes, your own harness, or optionally SkillLite. Evotown does not require a specific upstream; use the ingest API to attach runners. Economy rules are configurable, reproducible, fully local, and do not depend on virtual/cryptocurrency. Evotown — Evolution Arena Language: English | 中文 Prerequisites Python 3.10+ Node.js 18+ Skills workspace: backend expects a project tree with or (layout depends on the agent backend you wire in). SkillLite (optional): only if you drive agents with the SkillLite CLI — then / and the default per-agent copy under apply. Other engines use their own install paths and report via HTTP ingest instead. Quick Start Option A — Docker (Recommended) Requires Docker Desktop (or Docker Engine + Compose plugin). bash cd evotown Create .env from the template (same directory as docker-compose.yml) cp .env.example .env Edit APIKEY / BASEURL / MODEL, and optional per-channel overrides (JUDGE, DISPATCHER, SOCIAL, CHRONICLE) First-time: build images and start docker compose up -d --build Subsequent starts (no rebuild needed)
| Stars | 648 |
| Forks | 64 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 68.9193904535691/100 |
| Open Issues | 33 |
| Last Updated | 2026-09-14 |
| Created | 2026-03-02 |
| Platforms | docker, python |
| Est. Tokens | ~15k |
These tools work well together with evotown for enhanced workflows:
Looking for a evotown alternative? If you're comparing evotown with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verifi
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
A Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource pr
MUE-X - self-evolving AI agent. Standalone CLI works anywhere. No Claude Code needed. Gemini & Copilot adapter
General-purpose Playwright automation for coding agents
Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents
Explore other popular codex skill tools:
evotown is a middle platform for enterprise Agent runtime governance and capability assets — connect OpenClaw, Hermes, SkillLite, and custom runtimes in one place; accumulate Skills and enterprise knowledge; pro. It is categorized as a Codex Skill with 648 GitHub stars.
evotown is primarily written in Python. It covers topics such as agent-skills, evolution, runtime-governance.
You can find installation instructions and usage details in the evotown GitHub repository at github.com/EXboys/evotown. The project has 648 stars and 64 forks, indicating an active community.
The top alternatives to evotown on Agent Skills Hub include COG-second-brain, AutoSkill, Awesome-Self-Evolving-Agents. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: