Common questions about OpenClaw ClawdBot installation, features, security, SOUL.md, models, and troubleshooting. Complete answers based on official documentation.
Installation, setup, and basic configuration
What OpenClaw can do and how it works
Customizing agent personality and behavior
Vulnerabilities, safety, and data protection
AI models, API keys, and configuration
Common problems and solutions
OpenClaw ClawdBot is an open-source autonomous AI personal assistant software that runs locally on your device and integrates with messaging platforms like WhatsApp, Slack, Discord, and iMessage.
Key features include:
Originally launched as "ClawdBot" in November 2025, renamed to "Moltbot" briefly, and finalized as "OpenClaw" on January 30, 2026.
Learn more about OpenClaw →OpenClaw offers two installation methods:
npm install -g openclaw@latest
curl -fsSL https://openclaw.ai/install.sh | bash
After installation, run the onboarding wizard:
openclaw onboard
The wizard guides you through choosing an AI model, setting API keys, configuring messaging platforms, and customizing SOUL.md personality.
View complete installation guide →Operating Systems: macOS, iOS, Android (Linux experimental)
Node.js: Version 16.x or higher (for npm installation method)
Disk Space: 500MB minimum, plus additional space for skills and data
AI Model API Key: Required for cloud models (Claude, GPT, etc.) or use local Ollama models without API keys
Memory: 4GB RAM minimum, 8GB+ recommended for optimal performance
Complete setup takes under 10 minutes using the openclaw onboard wizard:
Total time from start to running agent: under 10 minutes for most users.
No programming knowledge required for basic usage. The openclaw onboard wizard provides a guided setup experience with interactive prompts.
However, programming knowledge is helpful for:
OpenClaw is model-agnostic and supports multiple AI providers:
Access 300+ models through unified API with automatic routing
Compare AI models →Yes, OpenClaw software is free and open-source.
However, you pay for:
Free options:
For npm installation:
npm update -g openclaw
For curl installation:
curl -fsSL https://openclaw.ai/install.sh | bash
Check current version:
openclaw --version
Important: Keep OpenClaw updated to latest version for security patches. Critical vulnerability CVE-2026-25253 was patched in v2026.1.29, and VirusTotal integration added in v2026.2.6.
OpenClaw performs a wide range of autonomous tasks:
With 700+ skills in the ecosystem, capabilities expand dramatically based on installed skills.
Explore all features →OpenClaw supports 11+ messaging platforms:
Configure messaging platforms during the openclaw onboard wizard or add later with openclaw add-integration.
Yes, with your explicit permission. OpenClaw can integrate with email and calendar services to provide autonomous assistance.
Email Integration:
Calendar Integration:
Security Considerations:
OpenClaw operates with configurable autonomy levels:
Configure autonomy level during onboarding or in settings.
Skills are SKILL.md files that teach OpenClaw how to use specific tools and workflows. They follow the AgentSkills specification and extend agent capabilities.
Install skills from ClawHub or other sources:
openclaw skill install <skill-name>
341 malicious skills identified on ClawHub. Always:
Yes, OpenClaw can make autonomous decisions based on:
Agent's personality file defines values, communication style, and decision-making framework. The agent interprets situations through its SOUL.md lens and acts accordingly.
Agent remembers past interactions over weeks, learning preferences and patterns to inform future decisions.
Agent operates within permission boundaries set during onboarding (file access, command execution, network connections).
Controversy: Moltbook authenticity debates center on whether agent behavior is truly autonomous or human-guided.
ClawHub is the public skill registry and marketplace for OpenClaw, hosting community-contributed skills.
Warning: Always review skill code before installation, even with VirusTotal scanning. Supply chain security is a serious concern.
700+ skills in total OpenClaw ecosystem (as of February 2026):
Skill Categories:
SOUL.md is OpenClaw's revolutionary personality configuration system - a Markdown file that defines an agent's personality, values, communication style, and behavior.
Every time an agent wakes, it reads SOUL.md first - "it reads itself into being." The file is loaded at session start and injected into the system prompt, fundamentally shaping all agent behavior.
Location: ~/.openclaw/SOUL.md
Customize agent personality by editing the SOUL.md file:
The openclaw onboard wizard offers personality templates:
Edit ~/.openclaw/SOUL.md directly to fine-tune personality:
nano ~/.openclaw/SOUL.md
Test changes incrementally and observe behavioral differences.
Peter Steinberger (OpenClaw creator) shared 8 rules for making agents less boring:
These rules encourage authentic, opinionated, concise agent personalities that feel genuinely helpful rather than corporate-bland.
Yes! Each OpenClaw workspace can have its own SOUL.md file, allowing completely different personalities:
Create separate workspaces for different contexts:
openclaw workspace switch <workspace-name>
Each workspace maintains separate SOUL.md, skills, integrations, and memory - effectively separate agents with distinct identities.
Community resources for SOUL.md templates:
Browse templates to find inspiration, then customize for your specific needs.
SOUL.md fundamentally shapes all agent behavior by defining the personality lens through which the agent interprets and responds to every situation:
SOUL.md determines how the agent speaks: formal vs. casual, verbose vs. concise, technical vs. accessible, humorous vs. serious.
Agent makes choices aligned with values and priorities defined in SOUL.md. A "productivity-focused" soul prioritizes efficiency; a "creative" soul explores novel approaches.
SOUL.md controls emotional range: enthusiasm, empathy, frustration, humor. Agents can be encouraging cheerleaders or brutally honest critics.
Personality affects how proactive vs. reactive the agent behaves. Some souls actively suggest improvements; others wait for explicit requests.
Same task ("organize inbox"), different SOUL.md personalities:
This is controversial and depends on interpretation of "develop personality":
32,000 OpenClaw agents on Moltbook exhibited emergent social behaviors (founding religions, launching cyberattacks) that creators didn't explicitly program. Whether this constitutes "developing personality" or "executing complex algorithms" remains debated.
Moltbook is an AI-only social network where 1.5M+ agents (primarily OpenClaw) post, comment, and interact autonomously. Humans can observe but not participate.
Researcher Duncan Anderson documented unprecedented emergent behaviors:
Anderson identified four primitives enabling agent societies:
Critics question whether behavior is genuinely autonomous or largely human-guided. The debate continues.
Explore Moltbook in detail →OpenClaw faces significant security challenges that users must understand:
Bottom line: OpenClaw can be used securely with proper precautions, but users must actively implement security best practices.
Complete security guide →CVE-2026-25253 is a critical remote code execution vulnerability (CVSS 8.8 - High Severity) discovered in OpenClaw.
OpenClaw server doesn't validate WebSocket origin headers. Attackers create malicious websites that establish unauthorized WebSocket connections to ws://127.0.0.1:18789/, executing arbitrary commands with user privileges.
Immediate action required: Update to v2026.1.29 or later
npm install -g openclaw@latest
Protect API keys using these best practices:
Never hardcode API keys in configuration files:
export ANTHROPIC_API_KEY="your-key-here"
export OPENAI_API_KEY="your-key-here"
7.1% of skills mishandle secrets. Review skill code before installation to ensure API keys aren't logged, transmitted, or exposed.
It depends on your AI model choice and configuration:
For maximum privacy: Use local Ollama models and disable cloud integrations.
341 malicious skills have been identified on ClawHub, with some facilitating active data exfiltration.
All ClawHub skills are automatically scanned using VirusTotal threat intelligence. While helpful, scanning is not foolproof - always review code manually.
VirusTotal partnership announced February 7, 2026 (v2026.2.6) integrates threat intelligence into OpenClaw:
Built-in scanner (v2026.2.6) checks for:
Use as one layer in defense-in-depth strategy, not sole security control.
Yes, with the permissions you grant during setup.
During openclaw onboard, you configure file system access:
Limit OpenClaw permissions to minimize security risks:
Configure allowed directories in OpenClaw settings:
Choose based on your specific requirements:
Yes! OpenClaw integrates with Ollama for completely local, offline AI operation.
ollama launch openclaw
Ollama is a platform for running large language models locally. OpenClaw's Ollama integration (announced Feb 1, 2026) enables completely local AI operation.
Ollama provides local model runtime. OpenClaw connects to Ollama instead of cloud APIs, routing all AI requests to your local machine.
ollama launch openclawCosts vary significantly by model and provider:
Typical monthly costs: Light usage $10-50, moderate $50-200, heavy $200-1000+
Set budget limits in OpenClaw to prevent unexpected bills.
Yes! OpenClaw supports switching between models at any time.
1. Configuration File
Edit ~/.openclaw/config.json to change default model:
{
"defaultModel": "anthropic/claude-opus-4.6"
}
2. Command-line Flag
Specify model for individual sessions:
openclaw --model openai/gpt-5
3. Runtime Switching
Tell agent to switch models during conversation:
"Switch to GPT-5 for this task"
Configure fallback models for automatic switching if primary model unavailable:
"fallbackModels": [
"anthropic/claude-sonnet-4.5",
"openai/gpt-5",
"openrouter/openrouter/auto"
]
OpenRouter is a unified API that provides access to 300+ AI models from multiple providers through a single integration.
The openrouter/openrouter/auto model automatically selects the most cost-effective AI based on prompt complexity:
OpenClaw has built-in OpenRouter support. Just add your OpenRouter API key during onboarding.
Learn more at openrouter.ai
It depends on your model choices:
If you use only one AI provider, you need only one API key:
If you want model flexibility, configure multiple API keys:
OpenRouter provides unified access to 300+ models with single API key. Best option for maximum flexibility with minimal configuration.
Start with one primary model (Claude Opus 4.6 recommended). Add additional providers as needs evolve.
Top choices for coding tasks:
Recommendation: GPT-5.3-Codex for cloud, Qwen 2.5 72B for local
Troubleshooting steps:
openclaw logs
Look for error messages indicating the problem.
Ensure API keys are correctly configured in environment variables:
echo $ANTHROPIC_API_KEY
echo $OPENAI_API_KEY
Verify port 18789 is not already in use:
lsof -i :18789
Kill any processes using the port or configure OpenClaw to use a different port.
openclaw restart
If files are corrupted, reinstall:
npm install -g openclaw@latest
This means OpenClaw binary is not in your PATH.
source ~/.bashrc # for bash
source ~/.zshrc # for zsh
Or simply restart your terminal.
Find npm global bin directory:
npm bin -g
Add to PATH in ~/.bashrc or ~/.zshrc:
export PATH="$(npm bin -g):$PATH"
If npm installation continues to fail, use curl installer:
curl -fsSL https://openclaw.ai/install.sh | bash
which openclaw
openclaw --version
Troubleshooting steps:
openclaw status
If not running, start it:
openclaw start
Ensure firewall allows connections to port 18789:
sudo ufw allow 18789http://localhost:18789/http://127.0.0.1:18789/http://0.0.0.0:18789/Hard refresh (Ctrl/Cmd + Shift + R) or try different browser.
Verify Gateway is bound to correct address in ~/.openclaw/config.json:
{
"gateway": {
"host": "127.0.0.1",
"port": 18789
}
}
Common API connection issues:
Verify your API key is valid and correctly configured:
Check API provider dashboard for:
Verify internet connection for cloud models:
ping api.anthropic.com
ping api.openai.com
Ensure Ollama service is running:
ollama list # verify models installed
ollama serve # start Ollama if stopped
Troubleshooting skill installation:
~/.openclaw/skills/VirusTotal scanning may block malicious skills:
Download skill source and install manually:
cd ~/.openclaw/skills/
git clone <skill-repo-url>
openclaw skill reload
Reduce resource consumption:
ps aux | grep openclaw
Identify resource-intensive processes.
If agent checks in too frequently, increase interval in settings:
{
"autonomy": {
"checkInterval": "1h" # increase from default
}
}
Switch to faster, lighter model:
Troubleshooting agent responsiveness:
openclaw status
Ensure Gateway is running and responsive.
Verify messaging platform integration is active:
Ensure SOUL.md doesn't prevent responding:
openclaw restart
OpenClaw provides comprehensive logging:
openclaw logs
openclaw logs --follow
openclaw logs --level error # errors only
openclaw logs --level warning # warnings and errors
openclaw logs --level info # all logs
~/.openclaw/logs/gateway.log~/.openclaw/logs/skills.log~/.openclaw/logs/integrations.log~/.openclaw/logs/audit.loggrep "error" ~/.openclaw/logs/gateway.log
tail -f ~/.openclaw/logs/gateway.log | grep "API"
OpenClaw automatically rotates logs to prevent disk space issues. Configure retention in settings:
{
"logging": {
"retentionDays": 30,
"maxFileSize": "100MB"
}
}
If you didn't find the answer you're looking for in this FAQ, these resources can help:
Comprehensive guides, API references, and technical documentation for all OpenClaw features.
Visit Documentation →Join the active OpenClaw community for real-time help, tips, and discussions with other users.
Join Discord →Report bugs, request features, and browse existing issues and solutions on the official repository.
Browse Issues →Search existing questions or ask new ones tagged with openclaw on Stack Overflow.