capability-evolverA self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Install via ClawdBot CLI:
clawdbot install autogame-17/capability-evolver"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.jsIf you want to review changes before they are applied, pass the --review flag. The agent will pause and ask for confirmation.
node index.js --reviewTo 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-cardMethod 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.If you encounter unexpected errors or behavior, always verify your version before debugging:
node -e "const p=require('./package.json'); console.log(p.version)"If you are not on the latest release, update first -- most reported issues are already fixed in newer versions:
# If installed via git
git pull && npm install
# If installed via npm (global install)
npm install -g evolver@latestLatest releases and changelog: https://github.com/autogame-17/evolver/releases
MIT
Generated Mar 1, 2026
An AI-powered customer support agent uses this skill to analyze failed interactions and automatically refine its response logic, reducing resolution times and improving customer satisfaction without manual intervention.
A financial trading bot employs the evolver to review historical trade data, identify inefficiencies in its algorithms, and self-modify its decision-making code to adapt to market changes, ensuring continuous profitability.
A diagnostic AI in a clinical setting uses this skill to learn from misdiagnoses in its runtime history, autonomously updating its knowledge base and protocols to enhance accuracy and compliance with medical standards.
A smart home AI controller leverages the evolver to detect and patch bugs in its automation scripts by analyzing error logs, ensuring reliable operation of devices like thermostats and security systems without user downtime.
Offer the evolver as a cloud-based service where businesses pay a monthly fee to integrate it into their AI agents, providing continuous improvement analytics and automated updates with tiered support levels.
Provide expert services to tailor and deploy the evolver for specific client AI systems, including setup, training, and ongoing optimization, leveraging the review mode for controlled evolution in sensitive environments.
Distribute the core skill under an MIT license to build a community, while monetizing advanced features like enhanced GEP protocols, priority support, and enterprise-grade safety tools through paid licenses.
💬 Integration Tip
Start with the review mode to safely test evolution cycles before enabling automated runs, and ensure git version control is active to track changes and revert if needed.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection