EvolveClaw

A self-evolving, personalized OpenClaw

The more you use it, the better it understands you.

📰 News

• [2026/03] 🔥 Fully automatic setup — The plugin now auto-starts the SCOPE server and auto-detects OpenClaw's model configuration. No .env, no manual server launch needed!
• [2026/03] 🔥 Added custom SCOPE prompts & domains tailored for personal AI assistants — user preference learning, code quality analysis, and communication style optimization!
• [2026/03] 🚀 EvolveClaw v1 released! Self-evolving prompt system for OpenClaw with zero code modification — plugin + sidecar architecture powered by SCOPE.

EvolveClaw turns OpenClaw into a self-improving agent that continuously adapts to your workflows. Powered by SCOPE (Self-evolving Context Optimization via Prompt Evolution), it observes how you interact with the agent — your tasks, your tool usage patterns, your preferences — and automatically evolves the system prompt with personalized guidelines that make the agent increasingly effective for you, not just any user.

No two EvolveClaw instances are the same. Over time, each one develops a unique personality shaped by its owner's habits.

Key adaptation: SCOPE was originally designed for task-specific benchmarks (e.g., HLE). EvolveClaw extends it with custom prompt templates and domain categories tailored for a personal AI coding assistant — focusing on user preference learning, code quality, communication style, and workflow patterns instead of domain-specific problem-solving heuristics.

📝 Contents

• 💡 Why EvolveClaw?
• ⚙️ How It Works
• 🚀 Quick Start
• 🧬 What Makes It Self-Evolving
• 🏗️ Architecture
• 🎯 Design Decisions
• 🔌 API Endpoints
• 📖 Citation

💡 Why EvolveClaw?

Today's AI coding agents ship with a static system prompt — every user gets the same instructions. But users are different: some prefer terse answers, others want detailed explanations; some rely heavily on search tools, others write code directly; some work on frontends, others on distributed systems.

EvolveClaw closes this gap with three core ideas:

⚙️ How It Works

1. Observe — The plugin captures your full interaction trace: model output, tool calls, tool results, errors, and the semantic nature of your task
2. Learn — SCOPE analyzes each trace and synthesizes a guideline if warranted — e.g., "When this user asks for refactoring, prefer small atomic commits over large rewrites"
3. Classify — Each guideline is classified as tactical (task-specific, ephemeral) or strategic (cross-task, persisted to disk as part of your personal memory)
4. Inject — On the next turn, all active guidelines are injected into the system prompt, structured by priority (strategic > tactical)
5. Forget — When you start a new session, tactical guidelines are cleared. The agent remembers who you are (strategic), not what you were doing yesterday (tactical)

This creates a virtuous cycle: the more you use the agent, the better it understands your preferences, and the more personalized its behavior becomes.

🚀 Quick Start

0. Prerequisites — Install OpenClaw

EvolveClaw requires a running OpenClaw instance. If you don't have one yet:

# Requires Node ≥ 22
npm install -g openclaw@latest

# Run the onboarding wizard (sets up gateway, workspace, channels)
openclaw onboard --install-daemon

For more details, see OpenClaw Getting Started. You'll also need Python ≥ 3.10 for the SCOPE sidecar server.

1. Install the Plugin

Option A — From ClawHub (recommended):

openclaw plugins install clawhub:evolveclaw
pip install -r ~/.openclaw/extensions/evolveclaw/server/requirements.txt
openclaw gateway restart

Option B — From local source:

git clone https://github.com/JarvisPei/EvolveClaw.git
cd EvolveClaw
pip install -r server/requirements.txt
./scripts/install-plugin.sh
openclaw gateway restart

The plugin auto-starts the SCOPE server when it loads. It detects the server/ directory relative to the plugin source, spawns python3 server.py, and waits for it to be ready. No manual server launch needed.

Tip: If you prefer to manage the server process yourself (e.g., for custom .env settings or running on a different host), start it manually before OpenClaw and set "autoStartServer": false in the plugin config. The plugin detects a running server via /health and skips spawning.

{
  "plugins": {
    "entries": {
      "evolveclaw": {
        "enabled": true,
        "config": {
          "serverUrl": "http://127.0.0.1:5757",
          "agentName": "openclaw-agent",
          "injectMode": "append_system",
          "maxGuidelines": 30,
        }
      }
    }
  }
}

🧬 What Makes It Self-Evolving

Unlike static prompt engineering or manual rule files, EvolveClaw implements a self-improvement loop with the following components:

evolveclaw/
├── package.json               # npm/ClawHub package manifest
├── openclaw.plugin.json       # Plugin manifest with config schema
├── plugin/                    # OpenClaw TypeScript plugin
│   └── src/
│       ├── index.ts           # Plugin entry: lifecycle hooks, guideline management
│       ├── scope-client.ts    # HTTP client for SCOPE sidecar
│       └── types.ts           # Shared type definitions (config, API, guideline metadata)
├── server/                    # SCOPE sidecar HTTP server (Python)
│   ├── server.py              # FastAPI server: step analysis, tactical reset, stats
│   ├── config.py              # Server configuration (env vars)
│   ├── prompts.py             # Custom SCOPE prompts & domains for personal assistant use
│   ├── requirements.txt
│   └── .env.template          # Environment variable template
└── scripts/
    ├── start-server.sh        # Start the SCOPE sidecar
    └── install-plugin.sh      # Auto-configure OpenClaw to load the plugin

📋 TODOs and Known Limitations

• Feedback loop — No auto-feedback from the plugin (OpenClaw has no user_feedback hook). Could be added once SCOPE supports guideline removal or OpenClaw adds a feedback hook.
• Migrate to focused SDK subpaths — OpenClaw v2026.3.22 introduced openclaw/plugin-sdk/* subpaths (e.g., openclaw/plugin-sdk/plugin-entry) as the recommended import surface. Our plugin uses the monolithic openclaw/plugin-sdk which is still fully supported. Once installed via ClawHub, the focused subpaths can be adopted.

🔧 Compatibility

🔗 Related Projects

• SCOPE — The prompt evolution framework powering EvolveClaw
• OpenClaw — The AI agent platform

📖 Citation

@software{pei2026evolveclaw,
  title={EvolveClaw: Evolving OpenClaw's System Prompt via Self-Improving Guidelines},
  author={Pei, Zehua and Zhen, Hui-Ling},
  url={https://github.com/JarvisPei/EvolveClaw},
  year={2026}
}

@article{pei2025scope,
  title={SCOPE: Prompt Evolution for Enhancing Agent Effectiveness},
  author={Pei, Zehua and Zhen, Hui-Ling and Kai, Shixiong and Pan, Sinno Jialin and Wang, Yunhe and Yuan, Mingxuan and Yu, Bei},
  journal={arXiv preprint arXiv:2512.15374},
  year={2025}
}

⚖️ License

MIT