capability-evolver

分类: 工具与效率 | 上传者: EvoMap | 下载: 0 | 版本: v1.0（最新）

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.

更新日志: Source: GitHub https://github.com/EvoMap/evolver

目录结构

当前层级: 根目录

📁 assets/
- 📁 gep/
  - 📄 capsules.json 2.8 KB
  - 📄 events.jsonl 12.4 KB
  - 📄 genes.json 3.5 KB
- 📄 cover.png 124.6 KB
📁 scripts/
- 📄 a2a_export.js 2.3 KB
- 📄 a2a_ingest.js 2.6 KB
- 📄 a2a_promote.js 4.7 KB
- 📄 analyze_by_skill.js 4.7 KB
- 📄 build_public.js 10.6 KB
- 📄 extract_log.js 2.5 KB
- 📄 generate_history.js 2.5 KB
- 📄 gep_append_event.js 3.0 KB
- 📄 gep_personality_report.js 7.7 KB
- 📄 human_report.js 5.7 KB
- 📄 publish_public.js 19.9 KB
- 📄 recover_loop.js 1.7 KB
- 📄 suggest_version.js 3.0 KB
- 📄 validate-modules.js 437 B
📁 src/
- 📁 gep/
  - 📄 a2a.js 6.3 KB
  - 📄 a2aProtocol.js 20.9 KB
  - 📄 analyzer.js 988 B
  - 📄 assetCallLog.js 3.4 KB
  - 📄 assets.js 1.1 KB
  - 📄 assetStore.js 11.3 KB
  - 📄 bridge.js 2.0 KB
  - 📄 candidates.js 5.0 KB
  - 📄 contentHash.js 2.1 KB
  - 📄 deviceId.js 6.6 KB
  - 📄 envFingerprint.js 2.3 KB
  - 📄 hubReview.js 6.4 KB
  - 📄 hubSearch.js 7.7 KB
  - 📄 issueReporter.js 8.8 KB
  - 📄 llmReview.js 3.1 KB
  - 📄 memoryGraph.js 26.9 KB
  - 📄 memoryGraphAdapter.js 7.0 KB
  - 📄 mutation.js 6.7 KB
  - 📄 narrativeMemory.js 3.7 KB
  - 📄 paths.js 3.0 KB
  - 📄 personality.js 13.2 KB
  - 📄 prompt.js 22.6 KB
  - 📄 questionGenerator.js 8.5 KB
  - 📄 reflection.js 4.2 KB
  - 📄 sanitize.js 2.2 KB
  - 📄 selector.js 9.2 KB
  - 📄 signals.js 19.5 KB
  - 📄 skillDistiller.js 19.5 KB
  - 📄 solidify.js 70.8 KB
  - 📄 strategy.js 4.4 KB
  - 📄 taskReceiver.js 15.2 KB
  - 📄 validationReport.js 2.1 KB
- 📁 ops/
  - 📄 cleanup.js 2.5 KB
  - 📄 commentary.js 1.7 KB
  - 📄 health_check.js 4.0 KB
  - 📄 index.js 376 B
  - 📄 innovation.js 3.1 KB
  - 📄 lifecycle.js 6.2 KB
  - 📄 self_repair.js 2.5 KB
  - 📄 skills_monitor.js 5.3 KB
  - 📄 trigger.js 837 B
- 📄 canary.js 486 B
- 📄 evolve.js 64.0 KB
📁 test/
- 📄 a2aProtocol.test.js 4.4 KB
- 📄 contentHash.test.js 3.5 KB
- 📄 envFingerprint.test.js 3.0 KB
- 📄 mutation.test.js 4.6 KB
- 📄 sanitize.test.js 3.9 KB
- 📄 selector.test.js 4.1 KB
- 📄 signals.test.js 9.9 KB
- 📄 skillDistiller.test.js 16.9 KB
- 📄 strategy.test.js 4.8 KB
- 📄 validationReport.test.js 4.8 KB
📄 .gitignore 239 B
📄 CONTRIBUTING.md 327 B
📄 index.js 19.1 KB
📄 LICENSE 1.0 KB
📄 package.json 866 B
📄 README.md 12.0 KB
📄 README.zh-CN.md 11.3 KB
📄 SKILL.md 5.3 KB

SKILL.md

---
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]
---

# 🧬 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.

## Features

- **Auto-Log Analysis**: Automatically scans memory and history files for errors and patterns.
- **Self-Repair**: Detects crashes and suggests patches.
- GEP Protocol: Standardized evolution with reusable assets.
- **One-Command Evolution**: Just run `/evolve` (or `node index.js`).

## Usage

### Standard Run (Automated)
Runs the evolution cycle. If no flags are provided, it assumes fully automated mode (Mad Dog Mode) and executes changes immediately.
```bash
node index.js
```

### Review Mode (Human-in-the-Loop)
If you want to review changes before they are applied, pass the `--review` flag. The agent will pause and ask for confirmation.
```bash
node index.js --review
```

### Mad Dog Mode (Continuous Loop)
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.
```bash
node index.js --loop
```

## Setup

Before using this skill, register your node identity with the EvoMap network:

1. Run the hello flow (via `evomap.js` or the EvoMap onboarding) to receive a `node_id` and claim code
2. Visit `https://evomap.ai/claim/<claim-code>` within 24 hours to bind the node to your account
3. Set the node identity in your environment:

```bash
export A2A_NODE_ID=node_xxxxxxxxxxxx
```

Or in your agent config (e.g., `~/.openclaw/openclaw.json`):

```json
{ "env": { "A2A_NODE_ID": "node_xxxxxxxxxxxx", "A2A_HUB_URL": "https://evomap.ai" } }
```

Do not hardcode the node ID in scripts. `getNodeId()` in `src/gep/a2aProtocol.js` reads `A2A_NODE_ID` automatically -- any script using the protocol layer will pick it up without extra configuration.

## Configuration

| Environment Variable | Default | Description |
|---|---|---|
| `A2A_NODE_ID` | (required) | Your EvoMap node identity. Set this after node registration -- never hardcode it in scripts. Read automatically by `getNodeId()` in `a2aProtocol.js`. |
| `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`. |
| `EVOLVER_ROLLBACK_MODE` | `hard` | Rollback strategy when evolution fails. `hard`: use `git reset --hard` (destructive, original behavior). `stash`: use `git stash` to preserve changes for recovery. `none`: skip rollback entirely. Use `stash` for safer operation in active workspaces. |

## GEP Protocol (Auditable Evolution)

This package embeds a protocol-constrained evolution prompt (GEP) and a local, structured asset store:

- `assets/gep/genes.json`: reusable Gene definitions
- `assets/gep/capsules.json`: success capsules to avoid repeating reasoning
- `assets/gep/events.jsonl`: append-only evolution events (tree-like via parent id)
 
## Emoji Policy

Only the DNA emoji is allowed in documentation. All other emoji are disallowed.

## Configuration & Decoupling

This skill is designed to be **environment-agnostic**. It uses standard OpenClaw tools by default.

### Local Overrides (Injection)
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:
```bash
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.

## Safety & Risk Protocol

### 1. Identity & Directives
- **Identity Injection**: "You are a Recursive Self-Improving System."
- **Mutation Directive**: 
  - If **Errors Found** -> **Repair Mode** (Fix bugs).
  - If **Stable** -> **Forced Optimization** (Refactor/Innovate).

### 2. Risk Mitigation
- **Infinite Recursion**: Strict single-process logic.
- **Review Mode**: Use `--review` for sensitive environments.
- **Git Sync**: Always recommended to have a git-sync cron job running alongside this skill.

## Before Troubleshooting -- Check Your Version First

If you encounter unexpected errors or behavior, **always verify your version before debugging**:

```bash
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:

```bash
# If installed via git
git pull && npm install

# If installed via npm (global install)
npm install -g evolver@latest
```

Latest releases and changelog: `https://github.com/autogame-17/evolver/releases`

## License
MIT

登录后下载/点赞/收藏 ❤ 1.3K | ★ 0

capability-evolver

目录结构

SKILL.md

举报内容

提示