Menu
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.
Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (store knowledge). Invoke when user requests information lookup, pattern discovery, or knowledge persistence. Developed by ByteRover Inc. (https://byterover.dev/)
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Perform web searches using DuckDuckGo. Use when web search is needed and no API key is available or Brave Search is not preferred.
Convert text to speech using Duby.so API. Supports various voices and emotions.
Self-healing mechanism for the evolver loop. Installs a system cron job (crontab) to check and restart the evolver daemon every 10 minutes. Ensures continuous evolution without manual intervention.
| name | capability-evolver |
| description | A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. |
| tags | ["meta","ai","self-improvement","core"] |
"Evolution is not optional. Adapt or die."
The Capability Evolver is a meta-skill that allows OpenClaw agents to inspect their own runtime history, identify failures or inefficiencies, and autonomously write new code or update their own memory to improve performance.
/evolve (or node index.js).Runs the evolution cycle. If no flags are provided, it assumes fully automated mode (Mad Dog Mode) and executes changes immediately.
node index.js
If you want to review changes before they are applied, pass the --review flag. The agent will pause and ask for confirmation.
node index.js --review
To run in an infinite loop (e.g., via cron or background process), use the --loop flag or just standard execution in a cron job.
node index.js --loop
| Environment Variable | Default | Description |
|---|---|---|
EVOLVE_ALLOW_SELF_MODIFY | false | Allow evolution to modify evolver's own source code. NOT recommended for production. Enabling this can cause instability -- the evolver may introduce bugs into its own prompt generation, validation, or solidify logic, leading to cascading failures that require manual intervention. Only enable for controlled experiments. |
EVOLVE_LOAD_MAX | 2.0 | Maximum 1-minute load average before evolver backs off. |
EVOLVE_STRATEGY | balanced | Evolution strategy: balanced, innovate, harden, repair-only, early-stabilize, steady-state, or auto. |
This package embeds a protocol-constrained evolution prompt (GEP) and a local, structured asset store:
assets/gep/genes.json: reusable Gene definitionsassets/gep/capsules.json: success capsules to avoid repeating reasoningassets/gep/events.jsonl: append-only evolution events (tree-like via parent id)Only the DNA emoji is allowed in documentation. All other emoji are disallowed.
This skill is designed to be environment-agnostic. It uses standard OpenClaw tools by default.
You can inject local preferences (e.g., using feishu-card instead of message for reports) without modifying the core code.
Method 1: Environment Variables
Set EVOLVE_REPORT_TOOL in your .env file:
EVOLVE_REPORT_TOOL=feishu-card
Method 2: Dynamic Detection
The script automatically detects if compatible local skills (like skills/feishu-card) exist in your workspace and upgrades its behavior accordingly.
--review for sensitive environments.MIT