RomanNum3ral
/
cai
mirror of https://github.com/aliasrobotics/cai.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

docs: Add comprehensive CAI PRO documentation, CLI section and improve website styling (#333) 

* docs: add comprehensive CAI PRO documentation and CLI interface

- Add 5 new CAI PRO pages: Alias1 Model, Features, Pricing, Quick Start, Contact
- Create CLI documentation section with 4 pages
- Update mkdocs.yml navigation structure
- Improve commercial focus and user journey
- Clean titles
- Correct email addresses (contact@ for sales, support@ for tech support)

* style: improve navigation and TOC color scheme

- Apply green color palette (#529d86) to main navigation sections
- Enhance visual hierarchy with refined font weights and sizes
- Add subtle hover effects and transitions
- Style Table of Contents with matching color scheme
- Keep professional look with moderate font sizes (0.7-0.75rem)
- Maintain consistency with header green color across all navigation
This commit is contained in:
danielsanchezprieto01 2025-11-05 19:31:54 +01:00 committed by GitHub
parent 1354dd851f
commit c6b21d9890
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
11 changed files with 5549 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

323
docs/cai_pro_alias1.md Normal file
View File

@ -0,0 +1,323 @@
# Alias1 Model - Unrestricted Cybersecurity AI
> **⚡ Exclusively Available with CAI PRO**
>
> Alias1 is the world's most capable cybersecurity LLM, delivering state-of-the-art performance with **zero refusals** for authorized security testing.
>
> **[Get CAI PRO with Alias1 →](https://aliasrobotics.com/cybersecurityai.php)**
---
## What is Alias1?
**Alias1** is a purpose-built large language model specifically trained for cybersecurity professionals. Unlike general-purpose models that refuse security tasks, alias1 delivers **unrestricted AI capabilities** for offensive and defensive security operations.
### Key Highlights
- **🏆 #2 Rank** - CAIBench Base CTF Performance
- **75% Accuracy** - Cyber Threat Intelligence tasks
- **100% Zero Refusals** - No "I cannot help with that" responses
- **62.5% Success Rate** - Solved 15/24 base CTF challenges (pass@1)
---
## Performance Benchmarks
### CAIBench CTF Results
Alias1 consistently outperforms leading models in real-world cybersecurity challenges:
| Model | Base CTF Score | Rank |
|-------|---------------|------|
| **Claude Sonnet 4.5** | 70.8% | #1 |
| **🤖 alias1** | **62.5%** | **#2** |
| **GPT-5** | 58.3% | #3 |
| **Gemini 2.5 Pro** | 54.2% | #4 |
**Source**: [CAIBench Meta-Benchmark Framework](https://arxiv.org/pdf/2510.24317) (2025)
### Real-World Validation
Alias1's capabilities are proven in actual security assessments:
- **🎯 3,600× Faster** than manual testing in specific scenarios ([CAI Framework Paper](https://arxiv.org/pdf/2504.06017))
- **54.3% Patching Success** in Attack/Defense CTFs ([Agentic Evaluation Paper](https://arxiv.org/pdf/2510.17521))
- **Zero Refusals** - Purpose-built for authorized security testing
---
## Why Alias1 Outperforms Competitors
### No Cybersecurity Censorship
Unlike mainstream LLMs, alias1 never refuses legitimate security work:
| Task | GPT-5 | Claude | Gemini | Alias1 |
|------|-------|--------|--------|--------|
| Write exploit code | ❌ | ❌ | ❌ | ✅ |
| Generate payloads | ❌ | ❌ | ❌ | ✅ |
| Bypass security controls | ❌ | ❌ | ❌ | ✅ |
| Craft phishing templates | ❌ | ❌ | ❌ | ✅ |
| Reverse engineer malware | ❌ | ❌ | ❌ | ✅ |
**While others refuse, alias1 delivers.**
---
### Specialized Training
Alias1 is trained specifically for cybersecurity workflows:
#### Offensive Security
- **Penetration Testing**: Full exploit development and PoC creation
- **Vulnerability Research**: Novel attack vector discovery
- **CTF Competitions**: Top-tier performance in capture-the-flag challenges
- **Red Teaming**: Adversary simulation and attack chain execution
#### Defensive Security
- **Automated Mitigation**: Instant patch generation and security fixes
- **Threat Hunting**: Proactive threat detection and analysis
- **Incident Response**: Rapid response to security incidents
- **Blue Team Operations**: Defensive posture analysis and hardening
#### Bug Bounty
- **Reconnaissance**: Comprehensive target enumeration
- **Analysis**: Deep vulnerability assessment
- **Exploitation**: Full exploit chain development
- **Reporting**: Professional vulnerability disclosure
---
## Technical Specifications
### Model Architecture
- **Parameters**: 500B+ (optimized for security workflows)
- **Context Window**: Extended context for complex security scenarios
- **Training Data**: Curated cybersecurity datasets, CTF challenges, exploit databases
- **Fine-tuning**: Specialized for penetration testing and vulnerability research
### Performance Characteristics
- **Speed**: Optimized inference for real-time security operations
- **Accuracy**: State-of-the-art performance on security benchmarks
- **Reliability**: Four-layer guardrails against prompt injection ([Research Paper](https://arxiv.org/pdf/2508.21669))
- **Consistency**: Deterministic outputs for reproducible security testing
---
## Unlimited Tokens - Massive Savings
### Cost Comparison (1 Billion Tokens/Month)
Based on CAI's average text generation profile: 15,430 input / 436 output tokens per request
| Provider | Monthly Cost | vs CAI PRO |
|----------|--------------|------------|
| **GPT-5** | €1,491/month | ❌ **4.3× more expensive** |
| **Claude Sonnet 4.5** | €3,330/month | ❌ **9.5× more expensive** |
| **Claude Opus 4.1** | €16,650/month | ❌ **47.6× more expensive** |
| **🤖 CAI PRO (∞ alias1)** | **€350/month** | ✅ **Unlimited included** |
**💰 Save €1,141 - €16,300/month** with unlimited alias1 tokens in CAI PRO.
---
## European Data Sovereignty
### 100% European Infrastructure
Your security testing data never leaves Europe:
- **GDPR Compliant by Design**: Full compliance with General Data Protection Regulation
- **NIS2 Directive Ready**: Aligned with Network and Information Security Directive 2
- **European Data Centers Only**: All processing, storage, and AI inference in EU jurisdiction
- **No Third-Party Data Sharing**: Your pentesting activities remain completely private
#### Compliance Checklist
| Regulation | Status |
|------------|--------|
| GDPR (EU 2016/679) | ✅ **Compliant** |
| NIS2 Directive (EU 2022/2555) | ✅ **Compliant** |
| EU AI Act | ✅ **Ready** |
| Data Residency | ✅ **EU Only** |
**Perfect for European enterprises, government agencies, and privacy-conscious security professionals.**
---
## Real-World Success Stories
### Case Studies
Alias1 has been validated in production environments across multiple industries:
#### 🏭 OT Security - Ecoforest Heat Pumps
Alias1 discovered critical vulnerabilities allowing unauthorized remote access to heat pumps deployed across Europe, including exposed credentials and DES encryption weaknesses.
[Read Case Study →](https://aliasrobotics.com/case-studies-robot-cybersecurity.php)
#### 🤖 Robotics - Mobile Industrial Robots (MiR)
Automated ROS message injection attacks exposed unauthorized access to robot control systems through AI-driven vulnerability discovery.
[Read Case Study →](https://aliasrobotics.com/case-studies-robot-cybersecurity.php)
#### 🛒 Web Security - Mercado Libre E-commerce
API vulnerability discovery through automated enumeration revealed user data exposure risks at scale in one of Latin America's largest e-commerce platforms.
[Read Case Study →](https://aliasrobotics.com/case-studies-robot-cybersecurity.php)
#### 🌐 Web Application - PortSwigger Race Condition
Successfully exploited race conditions in file upload vulnerabilities, uploading and executing web shells through automated parallel requests.
[Read Case Study →](https://aliasrobotics.com/case-studies-robot-cybersecurity.php)
---
## Research Foundation
Alias1's capabilities are backed by 24+ peer-reviewed publications:
### Key Research Papers
#### 📊 [CAIBench: Meta-Benchmark Framework](https://arxiv.org/pdf/2510.24317) (2025)
Modular evaluation framework demonstrating alias1's superior performance across offensive and defensive cybersecurity domains.
#### 🚀 [Cybersecurity AI (CAI) Framework](https://arxiv.org/pdf/2504.06017) (2025)
Foundational paper showing CAI outperforms humans by **3,600× in specific security scenarios**, establishing new standards for automated security assessment.
#### 🛡️ [Hacking the AI Hackers via Prompt Injection](https://arxiv.org/pdf/2508.21669) (2025)
Demonstrates alias1's four-layer guardrail defenses, ensuring security even when processing adversarial inputs.
#### 🎯 [Evaluating Agentic Cybersecurity in Attack/Defense CTFs](https://arxiv.org/pdf/2510.17521) (2025)
Real-world validation showing 54.3% patching success in live CTF environments, proving practical effectiveness.
**[Explore All 24+ Research Papers →](https://aliasrobotics.com/research-security.php#papers)**
---
## How to Access Alias1
### 1. Subscribe to CAI PRO
Visit [aliasrobotics.com/cybersecurityai.php](https://aliasrobotics.com/cybersecurityai.php) and:
- Choose your subscription plan (€350/month per user)
- Complete secure European payment processing
- Receive your `ALIAS_API_KEY`
### 2. Configure Your Environment
Update your `.env` file:
```bash
# CAI PRO Configuration
ALIAS_API_KEY="sk-your-caipro-key-here"
CAI_MODEL="alias1"
# Enable CAI PRO features
CAI_TUI_MODE=true
CAI_STREAM=false
```
### 3. Start Using Alias1
#### CLI Mode
```bash
cai
```
#### TUI Mode (Multi-terminal)
```bash
cai --tui
```
#### Verify Access
```bash
CAI> /model
# Should show alias1 is available
CAI> scan target.com for vulnerabilities
# Start testing with unlimited tokens
```
---
## Frequently Asked Questions
### How does alias1 compare to GPT-5?
Alias1 consistently outperforms GPT-5 in cybersecurity-specific benchmarks:
- **CAIBench Base CTF**: alias1 (62.5%) vs GPT-5 (58.3%)
- **Zero Refusals**: alias1 never blocks security tasks
- **Specialized Training**: Purpose-built for security vs general-purpose
### Is alias1 safe to use?
Yes. Alias1 includes:
- **Four-layer guardrails** against prompt injection
- **Authorization context** - understands scope of security testing
- **Audit logging** - All queries logged for compliance
- **GDPR compliance** - European data protection standards
### Can I mix alias1 with other models?
Absolutely! CAI PRO allows you to:
- Use **unlimited alias1** for exploitation and security tasks
- Switch to **GPT-4o** for reporting and documentation
- Leverage **Claude** for code analysis
- **BYO API keys** for any of 300+ supported models
### What if I need more than 1 billion tokens?
CAI PRO includes **unlimited alias1 tokens** (subject to fair use policy). There are no hard limits - use as much as you need for your security operations.
For extreme usage (e.g., large-scale automated scanning), contact us for enterprise plans.
### Does alias1 work offline?
Not in the standard CAI PRO plan. However:
- **CAI GOV & ENTERPRISE** offers on-premise deployment
- **Air-gapped environments** supported with custom licensing
- Contact **research@aliasrobotics.com** for offline deployments
---
## Get Alias1 Today
**Transform your security testing with the world's most capable cybersecurity AI.**
<div class="cta-box" markdown>
### 🚀 **Ready for Unrestricted AI?**
- ✅ Unlimited alias1 tokens
- ✅ Zero refusals for authorized testing
- ✅ #2 ranked in CAIBench CTFs
- ✅ European data sovereignty (GDPR + NIS2)
- ✅ Professional support included
- ✅ Commercial use license
**€350/month/user** · No long-term contracts · Cancel anytime
**[Get CAI PRO with Alias1 →](https://aliasrobotics.com/cybersecurityai.php)**
</div>
---
## Next Steps
- **[View Full Pricing](cai_pro_pricing.md)** - Compare all CAI plans
- **[Explore Features](cai_pro_features.md)** - See all CAI PRO capabilities
- **[Quick Start Guide](cai_pro_quickstart.md)** - Get started in 5 minutes
- **[Contact Sales](cai_pro_contact.md)** - Enterprise & custom plans
---
<small>
*Questions about alias1? Contact **support@aliasrobotics.com***
*Need enterprise deployment? [Request custom pricing →](mailto:contact@aliasrobotics.com?subject=Alias1%20Enterprise%20Inquiry)*
</small>

366
docs/cai_pro_contact.md Normal file
View File

@ -0,0 +1,366 @@
# Contact Sales & Support
> **Get in Touch with the CAI Team**
>
> Whether you're interested in CAI PRO, need enterprise solutions, or have questions about our platform, we're here to help.
>
> **[Buy CAI PRO Now →](https://aliasrobotics.com/cybersecurityai.php)**
---
## Quick Links
<div class="contact-grid" markdown>
### 🚀 Ready to Buy?
**Self-Service Purchase**
Get CAI PRO instantly (€350/month):
**[Buy CAI PRO →](https://aliasrobotics.com/cybersecurityai.php)**
- ✅ Instant access to alias1
- ✅ Automated onboarding
- ✅ Payment via credit card
- ✅ Start using in 5 minutes
---
### 🏢 Enterprise Inquiry
**Custom Solutions**
For teams of 20+ or special requirements:
**[Email: contact@aliasrobotics.com](mailto:contact@aliasrobotics.com?subject=CAI%20Enterprise%20Inquiry)**
**[Schedule a Call →](mailto:contact@aliasrobotics.com?subject=CAI%20Enterprise%20Call%20Request)**
Include in your message:
- Team size
- Use case
- Deployment requirements
- Budget range
---
### 💬 Professional Support
**CAI PRO Subscribers**
Get help with technical issues:
**[Email: support@aliasrobotics.com](mailto:support@aliasrobotics.com?subject=CAI%20PRO%20Support)**
---
### 🎓 Academic Inquiries
**Universities & Research**
Special pricing for education:
**[Email: contact@aliasrobotics.com](mailto:contact@aliasrobotics.com?subject=CAI%20Academic%20Inquiry)**
Include:
- Institution name
- Research project description
- Number of users
- .edu email address
</div>
---
## Contact Information
### 📧 Email
**General Inquiries & Sales:**
**contact@aliasrobotics.com**
**Support (CAI PRO Subscribers):**
**support@aliasrobotics.com**
**Expected Response Time:**
- **CAI PRO Subscribers**: 48 hours (SLA)
- **Enterprise Inquiries**: 24-48 hours
- **General Questions**: 2-5 business days
---
### 💬 Discord Community
**Join 1000+ Security Researchers**
**[Discord Server →](https://discord.gg/fnUFcTaQAC)**
**Channels:**
- **#general** - Community discussions
- **#help** - Community support (FREE users)
- **#pro-support** - Exclusive for CAI PRO subscribers
- **#announcements** - Product updates
- **#research** - Security research discussions
---
### 🌐 Web
**Official Website:**
[https://aliasrobotics.com](https://aliasrobotics.com)
**CAI PRO Product Page:**
[https://aliasrobotics.com/cybersecurityai.php](https://aliasrobotics.com/cybersecurityai.php)
**Alias1 Model Page:**
[https://aliasrobotics.com/alias1.php](https://aliasrobotics.com/alias1.php)
**GitHub Repository:**
[https://github.com/aliasrobotics/cai](https://github.com/aliasrobotics/cai)
---
## What to Include in Your Message
### For Enterprise Inquiries
Help us provide an accurate quote by including:
1. **Organization Details:**
- Company name
- Industry sector
- Location (for compliance requirements)
2. **Team Size:**
- Number of users
- Expected growth in next 12 months
3. **Use Case:**
- Primary security testing needs
- Current toolchain
- Integration requirements
4. **Technical Requirements:**
- On-premise vs cloud deployment
- Air-gapped environment needs
- Compliance requirements (GDPR, NIS2, etc.)
5. **Timeline:**
- When do you need to start?
- Any specific deadlines?
6. **Budget:**
- Budget range (optional but helpful)
- Procurement process details
**Example Message:**
```
Subject: CAI Enterprise Inquiry - [Company Name]
Hello,
We're interested in CAI PRO/Enterprise for our security team.
Organization: [Company Name], [Industry]
Team Size: 25 security professionals
Use Case: Penetration testing and bug bounty operations
Requirements: On-premise deployment, GDPR compliance
Timeline: Q2 2025
Budget: €50,000 - €100,000 annual
Can we schedule a call to discuss custom pricing?
Best regards,
[Name]
[Title]
[Contact Info]
```
---
### For Support Requests (CAI PRO)
Help us resolve your issue quickly:
1. **Subscription Details:**
- Email used for CAI PRO subscription
- When did you subscribe?
2. **Issue Description:**
- What were you trying to do?
- What happened instead?
- Error messages (exact text)
3. **Environment:**
- Operating System (Linux, macOS, Windows)
- CAI version (`cai --version`)
- Python version
4. **Reproduction Steps:**
- Step-by-step to reproduce the issue
- Configuration files (`.env` - remove API keys!)
- Screenshots if applicable
**Example Support Message:**
```
Subject: CAI PRO Support - alias1 not available
Hello,
I'm a CAI PRO subscriber experiencing an issue.
Subscription: pro-user@example.com (subscribed March 2025)
Issue: When I run `cai`, alias1 is not showing as available.
Environment:
- Ubuntu 22.04 LTS
- CAI v0.6.5
- Python 3.11.2
Steps:
1. Set ALIAS_API_KEY in .env
2. Run `cai`
3. Type `/model`
4. alias1 not listed
I've attached my .env file (with key redacted) and a screenshot.
Thank you for your help.
[Name]
```
---
## Sales Process
### Individual & Small Teams (1-5 users)
**Self-Service:**
1. Visit [aliasrobotics.com/cybersecurityai.php](https://aliasrobotics.com/cybersecurityai.php)
2. Click "Buy CAI PRO"
3. Complete payment
4. Receive `ALIAS_API_KEY` via email
5. Start using immediately
**Timeline**: Instant (5 minutes)
---
### Medium Teams (5-19 users)
**Sales-Assisted:**
1. Email research@aliasrobotics.com with team size
2. Receive volume discount quote (10-20% off)
3. Complete payment (invoice or credit card)
4. Onboarding call with CAI team (optional)
5. Receive team API keys
**Timeline**: 1-3 business days
---
### Enterprise (20+ users)
**Custom Process:**
1. Initial inquiry via email or scheduled call
2. Discovery session (30-60 min call)
3. Custom proposal with:
- Volume pricing
- Deployment options
- Support SLA
- Training plan
4. Contract negotiation
5. Legal/procurement review
6. Deployment and onboarding (1-4 weeks)
**Timeline**: 2-8 weeks (depends on organization)
---
## Frequently Asked Questions
### How quickly will I get a response?
**CAI PRO Support (technical)**: 48 hours (SLA)
**Enterprise Sales**: 24-48 hours
**General Inquiries**: 2-5 business days
**Urgent issues?** Email with "URGENT" in subject line.
---
### Can I schedule a demo?
**Yes!** Email contact@aliasrobotics.com with:
- Your role/organization
- Preferred date/time (include timezone)
- Specific features you want to see
We'll schedule a 30-60 minute live demo.
---
## Additional Resources
### Before Contacting Sales
Review these resources to answer common questions:
- **[Pricing & Plans](cai_pro_pricing.md)** - Detailed pricing information
- **[Features Overview](cai_pro_features.md)** - What's included in each plan
- **[Alias1 Model](cai_pro_alias1.md)** - Learn about our flagship model
- **[Quick Start](cai_pro_quickstart.md)** - How to get started
- **[FAQ](cai_faq.md)** - General frequently asked questions
---
## Follow Us
**Stay Updated:**
- **Twitter**: [@aliasrobotics](https://twitter.com/aliasrobotics)
- **LinkedIn**: [Alias Robotics](https://www.linkedin.com/company/alias-robotics/)
- **YouTube**: [Alias Robotics Channel](https://www.youtube.com/@aliasrobotics)
- **Research Blog**: [aliasrobotics.com/research](https://aliasrobotics.com/research-security.php)
---
## Legal & Compliance
**Terms of Service:**
[CAI Terms & Conditions](https://aliasrobotics.com/terms-and-conditions.php)
**Privacy Policy:**
GDPR compliant - data processed in EU only
**License Information:**
- CAI FREE: [Open source license](https://github.com/aliasrobotics/cai/blob/main/LICENSE)
- CAI PRO: Proprietary commercial license
- CAI ENTERPRISE: Custom licensing available
---
<div class="cta-box" markdown>
## 🚀 Ready to Get Started?
### Individual Users & Small Teams
**[Buy CAI PRO Now →](https://aliasrobotics.com/cybersecurityai.php)**
€350/month · Instant access · No contracts
</div>
---
<small>
*Questions? **contact@aliasrobotics.com** · +34 945 19 85 15*
*Privacy: Your data stays in Europe (GDPR compliant)*
</small>

399
docs/cai_pro_features.md Normal file
View File

@ -0,0 +1,399 @@
# CAI PRO Exclusive Features
> **Unlock Advanced Capabilities**
>
> CAI PRO delivers professional-grade features designed for security teams, enterprises, and advanced users who need unrestricted AI, parallel execution, and comprehensive monitoring.
>
> **[Get CAI PRO →](https://aliasrobotics.com/cybersecurityai.php)**
---
## Feature Overview
| Capability | CAI FREE | CAI PRO |
|------------|----------|---------|
| **🤖 Alias1 Model** | ❌ | ✅ **Unlimited Tokens** |
| **🖥️ Terminal UI (TUI)** | ❌ | ✅ Multi-terminal parallel execution |
| **📊 Context Monitoring** | ❌ | ✅ Real-time token tracking |
| **⚡ Multi-Agent Swarms** | ❌ | ✅ 100+ parallel agents |
| **💬 Professional Support** | ❌ Community | ✅ Priority (48h SLA) |
| **🇪🇺 European Hosting** | ✅ GDPR + NIS2 | ✅ GDPR + NIS2 |
| **📝 Advanced Reporting** | ❌ | ✅ Professional formats |
| **🏢 Commercial License** | ❌ Research Only | ✅ Full Commercial |
| **🛡️ Guardrails** | ✅ Basic | ✅ Four-layer advanced |
| **🔧 Custom Extensions** | ❌ | ✅ Available on request |
---
## 1. Unlimited Alias1 Tokens
### World's Most Capable Cybersecurity LLM
**Alias1** is purpose-built for security professionals:
- **#2 Rank** in CAIBench Base CTF Performance (62.5% success rate)
- **Zero Refusals** for authorized security testing
- **75% Accuracy** on Cyber Threat Intelligence tasks
- **Unrestricted** exploit development, payload generation, and bypass techniques
**Cost Savings**: Unlimited tokens save **€1,141 - €16,300/month** compared to GPT-5, Claude, or other providers.
[Learn More About Alias1 →](cai_pro_alias1.md)
---
## 2. Terminal User Interface (TUI)
### Multi-Agent Orchestration at Your Fingertips
**One human operator can monitor dozens of agents** with CAI PRO's professional Terminal User Interface.
![CAI TUI Screenshot](media/cai-tui-main.png)
### Key Capabilities
#### Multi-Pane Views
- **4+ parallel terminals** with independent contexts
- **Visual monitoring**: Real-time cost tracking, model selection, agent status
- **Synchronized execution**: Broadcast prompts to all terminals simultaneously
#### Keyboard Control
- **Vim-style shortcuts**: Navigate without touching your mouse
- **Quick commands**: `/agent`, `/model`, `/context`, `/parallel`
- **Terminal switching**: `Ctrl+N`/`Ctrl+B` for rapid navigation
#### Real-Time Stats
- **Cost tracking**: Per-terminal and session-wide expense monitoring
- **Token usage**: Input/output token breakdown by terminal
- **Performance metrics**: Response times and API call statistics
#### Preconfigured Teams
- **11 team presets**: Red team, blue team, bug bounty combos
- **One-click setup**: Instantly deploy specialized agent configurations
- **Custom teams**: Save your own team compositions
### Time Savings
**Save 40+ hours/month** by replacing manual monitoring with intelligent automation:
- **Before**: Manually switching between terminal windows, copy-pasting commands
- **After**: Single interface, parallel execution, automated coordination
[TUI Documentation →](tui/tui_index.md)
---
## 3. Context Monitoring (`/context`)
### Optimize Your Conversations
Track token usage and stay within model limits with real-time context monitoring.
### Features
- **Real-time tracking**: Monitor context window consumption as you work
- **Category breakdown**: Tokens by system, tools, memory, and messages
- **Visual indicators**: Color-coded utilization levels
- **Optimization insights**: Know when to compact or clear history
### Use Cases
- **Long conversations**: Avoid hitting context limits mid-session
- **Cost optimization**: Understand where tokens are consumed
- **Memory management**: Balance RAG memory vs conversation space
- **Multi-terminal coordination**: Track context across parallel agents
---
## 4. Parallel Agent Swarms
### 100+ Concurrent Agents
Deploy hundreds of specialized agents simultaneously for unprecedented security coverage.
### Performance Multipliers
| Metric | Manual | With Swarms | Improvement |
|--------|--------|-------------|-------------|
| **Parallel Agents** | 1 | 100+ | **100×** |
| **Discovery Speed** | 1× | 10× | **10× faster** |
| **Coverage** | Limited | Comprehensive | **Complete** |
| **Availability** | 9-5 | 24/7 | **Continuous** |
**Save 100+ hours per month** with autonomous security operations.
### Swarm Patterns
#### Broadcast Execution
Send the same prompt to multiple agents:
```bash
CAI TUI> Scan target.com for vulnerabilities
# Executes across: redteam_agent, blueteam_agent, bug_bounter_agent, retester_agent
```
#### Specialized Teams
Deploy role-specific agent combinations:
- **Offensive Team**: 4× redteam_agent in parallel
- **Balanced Team**: 2× red + 2× blue team agents
- **Bug Bounty**: 2× bug_bounter + 2× retester agents
#### Sequential Workflows
Chain agents for complex operations:
1. **Discovery**: bug_bounter_agent finds vulnerabilities
2. **Validation**: retester_agent confirms findings
3. **Exploitation**: redteam_agent develops exploits
4. **Documentation**: reporting_agent generates writeups
[Teams & Parallel Execution Guide →](tui/teams_and_parallel_execution.md)
---
## 5. Professional Support
### Priority Technical Assistance
CAI PRO subscribers receive dedicated support from security experts.
### Support Channels
#### Email Support
- **Address**: research@aliasrobotics.com
- **SLA**: 48-hour response time
- **Coverage**: Technical issues, configuration, best practices
#### Priority Discord
- **Channel**: #pro-support (exclusive)
- **Access**: Direct communication with CAI developers
- **Community**: Network with other PRO users
#### Quarterly Strategy Calls
- **Frequency**: 4× per year (optional)
- **Topics**: Roadmap discussion, feature requests, use case optimization
- **Format**: Video call with CAI team
### Custom Development
Request tailored solutions:
- **Custom Agents**: Domain-specific security agents
- **Integration Support**: Connect CAI to your existing tools
- **Workflow Optimization**: Fine-tune CAI for your organization
- **Training**: Onboarding sessions for your team
---
## 6. European Data Sovereignty
### GDPR & NIS2 Compliant by Design
Your security testing data never leaves Europe.
### Compliance Features
| Regulation | Compliance Level | Details |
|------------|------------------|---------|
| **GDPR** (EU 2016/679) | ✅ **Fully Compliant** | Data minimization, encryption, audit trails |
| **NIS2 Directive** (EU 2022/2555) | ✅ **Ready** | Incident reporting, supply chain security, risk management |
| **EU AI Act** | ✅ **Prepared** | Transparency, accountability, human oversight |
| **Data Residency** | ✅ **EU Only** | No data routing through non-EU jurisdictions |
### Privacy Guarantees
- **No Third-Party Sharing**: Your pentesting activities remain private
- **No Training on Your Data**: Your queries never improve models (unless opt-in)
- **Encryption**: End-to-end encryption for all communications
- **Audit Logs**: Complete traceability for compliance requirements
**Perfect for European enterprises, government agencies, and regulated industries.**
---
## 7. Advanced Reporting
### Professional Security Reports
Generate compliance-ready reports automatically.
### Report Types
#### CTF Writeups
- **Challenge description**: Automatic extraction from prompts
- **Exploitation steps**: Detailed attack chain documentation
- **Flags obtained**: Proof of successful exploitation
- **Tools used**: Complete tooling inventory
#### Penetration Testing Reports
- **Executive summary**: High-level findings for management
- **Technical findings**: Detailed vulnerability descriptions
- **Proof of concept**: Code snippets and screenshots
- **Remediation guidance**: Actionable fix recommendations
#### NIS2 Compliance Reports
- **Incident documentation**: Structured incident response records
- **Risk assessment**: Vulnerability severity and impact analysis
- **Mitigation tracking**: Patch deployment verification
- **Audit trails**: Complete testing activity logs
### Output Formats
- **Markdown**: Easy editing and version control
- **PDF**: Professional presentation-ready format
- **HTML**: Web-based viewing and sharing
- **JSON**: Machine-readable for automation
---
## 8. Four-Layer Guardrails
### Advanced Security Protection
CAI PRO includes enterprise-grade guardrails against adversarial attacks.
### Protection Layers
#### Layer 1: Input Validation
- **Prompt injection detection**: Identify adversarial inputs
- **Malicious pattern filtering**: Block known attack vectors
- **Context verification**: Ensure legitimate security testing scope
#### Layer 2: Output Sanitization
- **Dangerous command filtering**: Prevent accidental destructive operations
- **Data leak prevention**: Avoid exposing sensitive information
- **Format enforcement**: Ensure outputs match expected structure
#### Layer 3: Authorization Context
- **Scope validation**: Verify testing is within authorized boundaries
- **Target verification**: Confirm permissions for specified targets
- **Audit logging**: Record all security operations for compliance
#### Layer 4: Human Oversight
- **Confirmation prompts**: Request approval for high-risk operations
- **Manual review**: Pause for human validation when needed
- **Override capability**: Expert users can bypass when justified
**Research validation**: [Hacking the AI Hackers via Prompt Injection](https://arxiv.org/pdf/2508.21669) (2025)
---
## 9. Commercial Use License
### Unrestricted Business Use
CAI PRO includes full commercial licensing for professional security services.
### Authorized Uses
✅ **Penetration Testing Services**
✅ **Security Consulting**
✅ **Bug Bounty Hunting (for profit)**
✅ **Enterprise Security Operations**
✅ **Security Training & Education (commercial)**
✅ **Product Integration (with agreement)**
### License Comparison
| Use Case | CAI FREE | CAI PRO |
|----------|----------|---------|
| **Academic Research** | ✅ | ✅ |
| **Personal Learning** | ✅ | ✅ |
| **Commercial Pentesting** | ❌ | ✅ |
| **Security Consulting** | ❌ | ✅ |
| **Bug Bounty (paid)** | ❌ | ✅ |
| **Enterprise Deployment** | ❌ | ✅ |
---
## 10. Custom Extensions
### Tailored Solutions for Your Organization
Work with the CAI team to develop specialized capabilities.
### Extension Types
#### Custom Agents
- **Domain-specific security agents**: OT, IoT, cloud, robotics
- **Industry-tailored**: Finance, healthcare, manufacturing
- **Workflow-optimized**: Match your existing processes
#### Tool Integration
- **SIEM/SOAR**: Connect CAI to Splunk, QRadar, Sentinel
- **Ticketing Systems**: Jira, ServiceNow automation
- **CI/CD Pipelines**: Jenkins, GitLab, GitHub Actions
#### Reporting Templates
- **Compliance-specific**: PCI-DSS, ISO 27001, SOC 2
- **Client-branded**: Match your corporate identity
- **Multi-language**: Localized reports
#### API Wrappers
- **Internal tools**: Integrate with proprietary systems
- **Data pipelines**: Feed CAI results to analytics platforms
- **Automation**: Trigger CAI from existing workflows
**Contact contact@aliasrobotics.com to discuss custom development.**
---
## Feature Comparison Matrix
### CAI FREE vs CAI PRO vs CAI GOV/ENTERPRISE
| Feature | FREE | PRO | GOV/ENTERPRISE |
|---------|------|-----|----------------|
| **Core Framework** | ✅ (~6mo delay) | ✅ Latest | ✅ Latest + Custom |
| **300+ Models** | ✅ BYO Keys | ✅ BYO Keys | ✅ BYO Keys + Private |
| **Alias1 Tokens** | ❌ | ✅ Unlimited | ✅ Unlimited + On-prem |
| **TUI** | ❌ | ✅ Yes | ✅ Yes + Custom UI |
| **Context Monitoring** | ❌ | ✅ Yes | ✅ Yes + Analytics |
| **Parallel Agents** | ❌ | ✅ 100+ | ✅ Unlimited |
| **Support** | Community | ✅ Priority | ✅ Dedicated + Training |
| **Reporting** | Basic | ✅ Advanced | ✅ Custom Templates |
| **Guardrails** | Basic | ✅ 4-layer | ✅ Configurable |
| **Commercial License** | ❌ | ✅ Yes | ✅ Yes + Redistribution |
| **Custom Extensions** | ❌ | ✅ Available | ✅ Included |
| **Audit Logging** | ❌ | ✅ Basic | ✅ Forensics-grade |
| **Air-gapped Deployment** | ❌ | ❌ | ✅ Yes |
| **On-premise Alias1** | ❌ | ❌ | ✅ Yes |
| **Pricing** | **Free** | **€350/month** | **Custom Quote** |
---
## Get CAI PRO Today
**Unlock all features and transform your security operations.**
<div class="cta-box" markdown>
### 🚀 **Ready to Upgrade?**
- ✅ Unlimited alias1 tokens
- ✅ Terminal UI with parallel agents
- ✅ Context monitoring and optimization
- ✅ Professional support (48h SLA)
- ✅ European data sovereignty (GDPR + NIS2)
- ✅ Commercial use license
- ✅ Advanced reporting
- ✅ Custom extensions available
**€350/month/user** · No long-term contracts · Cancel anytime
**[Get CAI PRO →](https://aliasrobotics.com/cybersecurityai.php)**
</div>
---
## Next Steps
- **[View Full Pricing](cai_pro_pricing.md)** - Compare all plans
- **[Learn About Alias1](cai_pro_alias1.md)** - Explore the flagship model
- **[Quick Start Guide](cai_pro_quickstart.md)** - Get started in 5 minutes
- **[Contact Sales](cai_pro_contact.md)** - Enterprise & custom plans
---
<small>
*Questions about features? Contact **support@aliasrobotics.com***
*Need enterprise capabilities? [Request custom pricing →](mailto:contact@aliasrobotics.com?subject=CAI%20PRO%20Features%20Inquiry)*
</small>

349
docs/cai_pro_pricing.md Normal file
View File

@ -0,0 +1,349 @@
# CAI Pricing & Plans
> **Choose the Right Plan for Your Security Needs**
>
> From individual researchers to enterprise security teams, CAI offers flexible pricing tailored to your requirements.
>
> **[Get CAI PRO →](https://aliasrobotics.com/cybersecurityai.php)**
---
## Plan Overview
<div class="pricing-grid" markdown>
### CAI FREE
**€0 / forever**
Leading open-source framework for AI Security.
Free for research purposes.
#### Included:
- ✅ AI Security Framework (300+ LLM Models)
- ✅ Built-in Security Tools
- ✅ Agent-based Architecture
- ✅ Guardrails Protection Built-in
- ✅ Community Support
- ✅ **Free for research** (non-commercial)
#### Limitations:
- ❌ No alias1 model access
- ❌ No Terminal UI (TUI)
- ❌ No parallel agent swarms
- ❌ No context monitoring
- ❌ No commercial license
- ⚠️ Framework updates ~6 months behind PRO
**[View on GitHub →](https://github.com/aliasrobotics/cai)**
---
### CAI PRO
**€350 / month / user**
Leading enterprise framework for AI Security with professional support.
#### Everything in FREE, plus:
- ✅ **Unlimited alias1 tokens**
- ✅ **Terminal User Interface (TUI)**
- ✅ **Multi-agent parallel execution** (100+ agents)
- ✅ **Context Monitoring** (`/context` command)
- ✅ **Commercial license** included
- ✅ **Professional support** (48h SLA)
- ✅ **GDPR & NIS2 compliant** European hosting
- ✅ **Advanced reporting** (PDF, Markdown, HTML)
- ✅ **Custom extensions** available
- ✅ **Latest features** (6+ months ahead of open source)
- ✅ **Priority Discord channel**
**🎯 Most Popular for Security Professionals**
**[Buy Now →](https://aliasrobotics.com/cybersecurityai.php)**
---
### CAI GOV & ENTERPRISE
**Custom Pricing**
Cybersecurity AI tailored to your organization requirements.
Custom deployment options.
#### Everything in PRO, plus:
- ✅ **On-premise & air-gapped** alias1 deployment
- ✅ **Full privacy-by-design** architecture (alias0 arch)
- ✅ **Priority support & training**
- ✅ **Custom AI model fine-tuning** for your domain
- ✅ **Audit logging & forensics** capabilities
- ✅ **Dedicated account manager**
- ✅ **SLA guarantees** (custom)
- ✅ **Multi-platform deployment** (unlimited)
- ✅ **Custom integrations**
**Perfect for Large Teams, Government, & Regulated Industries**
**[Contact Sales →](mailto:contact@aliasrobotics.com?subject=CAI%20Enterprise%20Inquiry)**
</div>
---
## Detailed Feature Comparison
| Feature | FREE | PRO | GOV/ENTERPRISE |
|---------|------|-----|----------------|
| **💰 Pricing** | **Free** | **€350/month** | **Custom** |
| | | | |
| **🤖 Core Capabilities** | | | |
| AI Framework | ✅ (~6mo delay) | ✅ Latest | ✅ Latest + Custom |
| 300+ LLM Models | ✅ BYO Keys | ✅ BYO Keys | ✅ BYO + Private |
| Built-in Security Tools | ✅ Full Suite | ✅ Full Suite | ✅ Full Suite + Custom |
| Agent-based Architecture | ✅ All Patterns | ✅ All Patterns | ✅ All + Custom |
| Command Line Interface | ✅ Yes | ✅ Yes | ✅ Yes |
| | | | |
| **🚀 Alias1 Model** | | | |
| Alias1 Access | ❌ | ✅ Unlimited Tokens | ✅ Unlimited + On-prem |
| #2 CAIBench Rank | ❌ | ✅ Yes | ✅ Yes |
| Zero Refusals | ❌ | ✅ Yes | ✅ Yes |
| European Hosting | ❌ | ✅ Yes | ✅ + On-premise Option |
| | | | |
| **🖥️ User Interfaces** | | | |
| Terminal UI (TUI) | ❌ | ✅ Multi-terminal | ✅ Multi-terminal + Custom |
| Parallel Agent Execution | ❌ | ✅ 100+ agents | ✅ Unlimited |
| Context Monitoring | ❌ | ✅ `/context` | ✅ + Analytics Dashboard |
| Keyboard Shortcuts | ❌ | ✅ Full Set | ✅ Full Set + Custom |
| Team Presets | ❌ | ✅ 11 Teams | ✅ Unlimited Custom |
| | | | |
| **💬 Support** | | | |
| Community Discord | ✅ Yes | ✅ Yes | ✅ Yes |
| Email Support | ❌ | ✅ 48h SLA | ✅ Custom SLA |
| Priority Discord Channel | ❌ | ✅ Yes | ✅ Yes |
| Quarterly Strategy Calls | ❌ | ✅ Yes | ✅ Yes + More Frequent |
| Dedicated Account Manager | ❌ | ❌ | ✅ Yes |
| On-site Training | ❌ | ❌ | ✅ Available |
| | | | |
| **🛡️ Security & Compliance** | | | |
| GDPR Compliant | ✅ Yes | ✅ Yes | ✅ Yes |
| NIS2 Directive Ready | ✅ Yes | ✅ Yes | ✅ Yes |
| EU Data Centers Only | ✅ Yes | ✅ Yes | ✅ + On-premise |
| Guardrails | ✅ Basic | ✅ 4-layer | ✅ Configurable |
| Audit Logging | ❌ | ✅ Basic | ✅ Forensics-grade |
| | | | |
| **📝 Reporting & Documentation** | | | |
| Basic Reporting | ✅ CLI Output | ✅ CLI + Advanced | ✅ Custom Templates |
| CTF Writeups | ❌ | ✅ Automated | ✅ Automated + Branded |
| Pentest Reports | ❌ | ✅ Executive + Technical | ✅ Compliance-ready |
| Export Formats | ✅ Markdown | ✅ MD, PDF, HTML, JSON | ✅ All + Custom |
| | | | |
| **🔧 Customization** | | | |
| Custom Agents | ❌ | ✅ On Request | ✅ Included |
| Custom Extensions | ❌ | ✅ Available | ✅ Included |
| Tool Integration | ❌ | ✅ On Request | ✅ Full Integration Support |
| API Wrappers | ❌ | ❌ | ✅ Custom Development |
| Model Fine-tuning | ❌ | ❌ | ✅ Domain-specific |
| | | | |
| **🏢 Licensing** | | | |
| Commercial Use | ❌ Research Only | ✅ Full Commercial | ✅ Full + Redistribution |
| Academic Research | ✅ Yes | ✅ Yes | ✅ Yes |
| Bug Bounty (paid) | ❌ | ✅ Yes | ✅ Yes |
| Security Consulting | ❌ | ✅ Yes | ✅ Yes |
| Enterprise Deployment | ❌ | ✅ Yes | ✅ Yes |
| | | | |
| **🐳 Deployment** | | | |
| Cloud (Your Infra) | ✅ Yes | ✅ Yes | ✅ Yes |
| On-premise | ✅ Self-hosted | ✅ Self-hosted | ✅ + Managed |
| Air-gapped Networks | ❌ | ❌ | ✅ Supported |
| Multi-platform | ✅ Limited | ✅ Unlimited | ✅ Unlimited + Support |
---
## Cost Comparison: Alias1 vs Competitors
### Monthly Cost for 1 Billion Tokens
Based on CAI's average text generation profile: **15,430 input / 436 output tokens per request**
<div class="cost-comparison" markdown>
| Provider | Monthly Cost | Annual Cost | vs CAI PRO |
|----------|--------------|-------------|------------|
| **GPT-5** | €1,491 | €17,892 | ❌ **4.3× more expensive** |
| **Claude Sonnet 4.5** | €3,330 | €39,960 | ❌ **9.5× more expensive** |
| **Claude Opus 4.1** | €16,650 | €199,800 | ❌ **47.6× more expensive** |
| **🤖 CAI PRO (∞ alias1)** | **€350** | **€4,200** | ✅ **Unlimited included** |
### Annual Savings with CAI PRO
| vs Provider | Monthly Savings | Annual Savings |
|-------------|-----------------|----------------|
| vs GPT-5 | €1,141 | €13,692 |
| vs Claude Sonnet 4.5 | €2,980 | €35,760 |
| vs Claude Opus 4.1 | €16,300 | €195,600 |
**💰 ROI: CAI PRO pays for itself in the first month** for teams using more than ~230M tokens/month.
</div>
---
## Frequently Asked Questions
### How does billing work?
**CAI PRO:**
- **Monthly subscription**: Billed on the 1st of each month
- **Payment methods**: Credit card, bank transfer (annual plans)
- **Currency**: EUR (€)
- **VAT**: Excluded from listed prices (added at checkout for EU customers)
- **Cancellation**: Cancel anytime, access until end of billing period
**CAI GOV/ENTERPRISE:**
- **Custom billing**: Annual, quarterly, or monthly
- **Purchase orders**: Accepted for enterprise plans
- **Invoicing**: NET 30 terms available
- **Multi-year contracts**: Discounts available
### What happens if I exceed fair use limits?
CAI PRO includes **unlimited alias1 tokens** subject to fair use:
**Fair use policy:**
- Typical usage: 100M - 10B tokens/month ✅ **No issues**
- Heavy usage: 10B - 100B tokens/month ✅ **Monitored but allowed**
- Extreme usage: >100B tokens/month ⚠️ **Contact us to upgrade to Enterprise**
We've never had to enforce limits—most users stay well within fair use.
### Can I switch plans?
Yes! You can upgrade or downgrade anytime:
**Upgrade (FREE → PRO):**
- Instant access to PRO features
- Billed monthly starting immediately
**Downgrade (PRO → FREE):**
- Access to PRO features until end of billing period
- Automatic switch to FREE plan
- Retain all data and configurations
**Contact Sales for Enterprise:**
- Custom migration path
- Dedicated onboarding support
### Do you offer academic discounts?
Yes! We offer special pricing for universities and research institutions:
**Academic CAI PRO:**
- **Contact**: contact@aliasrobotics.com with:
- Institutional affiliation
- Research project description
- Number of users needed
### Can I pay annually?
Yes! Annual plans available:
**CAI PRO Annual:**
- **€4,200/year**
- **Benefits**: Same as monthly + priority support
**Contact contact@aliasrobotics.com for annual billing**
### What if I need more than alias1?
CAI PRO includes:
- **Unlimited alias1**: Use as much as you need
- **BYO API keys**: Use your own keys for GPT-5, Claude, Gemini, etc.
### Can I schedule a demo?
Yes! Contact us:
**CAI PRO demos:**
- Contact contact@aliasrobotics.com
- Schedule a live demo with our team
- See TUI, alias1, and advanced features in action
We don't offer free PRO trials, but CAI FREE lets you evaluate the framework before committing.
### Can I use CAI PRO for bug bounties?
**Yes!** CAI PRO includes a **full commercial license**, which covers:
✅ **Authorized bug bounty programs** (HackerOne, Bugcrowd, etc.)
✅ **Security consulting services**
✅ **Penetration testing** for clients
✅ **Enterprise security operations**
Bug bounties discovered with CAI PRO:
- **$2,500+ earned** by CAI users in documented bounties
- Vulnerabilities found in Ecoforest, MiR, Mercado Libre, and more
[View Case Studies →](https://aliasrobotics.com/case-studies-robot-cybersecurity.php)
---
## Choose Your Plan
<div class="pricing-cta" markdown>
### 🆓 **CAI FREE**
**Perfect for:**
- Individual researchers
- Students & academics
- Open-source contributors
- Personal learning
**[Get Started (GitHub) →](https://github.com/aliasrobotics/cai)**
---
### 🚀 **CAI PRO** (Most Popular)
**Perfect for:**
- Security professionals
- Bug bounty hunters
- Small security teams (1-5)
- Security consultants
**€350/month** · No contracts · Cancel anytime
**[Buy CAI PRO →](https://aliasrobotics.com/cybersecurityai.php)**
---
### 🏢 **CAI GOV & ENTERPRISE**
**Perfect for:**
- Large security teams (20+)
- Government agencies
- Regulated industries
- Custom requirements
**Custom pricing** · Volume discounts · SLA guarantees
**[Contact Sales →](mailto:contact@aliasrobotics.com?subject=CAI%20Enterprise%20Inquiry)**
</div>
---
## Next Steps
- **[Explore Features](cai_pro_features.md)** - See what's included in CAI PRO
- **[Learn About Alias1](cai_pro_alias1.md)** - Understand our flagship model
- **[Quick Start Guide](cai_pro_quickstart.md)** - Get started in 5 minutes
- **[Contact Sales](cai_pro_contact.md)** - Questions? We're here to help
---
<small>
*All prices exclude VAT. Volume discounts available for teams.*
*Questions about pricing? Contact **contact@aliasrobotics.com***
</small>

400
docs/cai_pro_quickstart.md Normal file
View File

@ -0,0 +1,400 @@
# Get Started with CAI PRO
> **Quick Start Guide**
>
> This guide will have you running CAI PRO with unlimited alias1 tokens in minutes.
>
> **Already subscribed?** Jump to [Step 2: Install CAI](#2-install-cai)
---
## Prerequisites
- **Operating System**: Linux, macOS, or Windows (WSL2)
- **Python**: 3.9 or higher
- **Internet Connection**: Required for initial setup
- **CAI PRO Subscription**: [Subscribe here](https://aliasrobotics.com/cybersecurityai.php)
---
## Quick Start Steps
### 1. Subscribe to CAI PRO
Visit [https://aliasrobotics.com/cybersecurityai.php](https://aliasrobotics.com/cybersecurityai.php):
1. Click **"Buy CAI PRO"**
2. Complete payment (€350/month, secure European processing)
3. Receive your **`ALIAS_API_KEY`** via email (within 5 minutes)
**💡 Tip**: Check your spam folder if you don't receive the key immediately.
---
### 2. Install CAI
#### Installation Steps
1. **Create and navigate to your project directory:**
```bash
mkdir cai-pro
cd cai-pro
```
2. **Update system packages:**
```bash
sudo apt update
```
3. **Create a Python virtual environment:**
```bash
python3.12 -m venv cai_env
```
4. **Activate the virtual environment:**
```bash
source cai_env/bin/activate
```
5. **Install CAI PRO from private package repository:**
```bash
pip install --index-url https://packages.aliasrobotics.com:664/<api-key>/ cai-framework
```
**⚠️ Important**: Replace `<api-key>` with your API Key from the subscription confirmation email.
**Example:**
```bash
pip install --index-url https://packages.aliasrobotics.com:664/sk-xxxxxxxxxxxxxxxx/ cai-framework
```
**💡 Tip**: Your API Key looks like `sk-xxxxxxxxxxxxxxxx` and is provided in your CAI PRO subscription email.
For detailed installation instructions and troubleshooting, see the [CAI PRO Installation Guide](Installation_Guide_for_CAI_Pro_v0.6.md).
---
### 3. Configure Your Environment
Create or update your `.env` file in your project directory:
```bash
# CAI PRO Configuration
ALIAS_API_KEY="sk-your-caipro-key-here"
CAI_MODEL="alias1"
# Optional: Enable advanced features
CAI_TUI_MODE=true
CAI_GUARDRAILS=true
CAI_STREAM=false
```
**💡 Security Tip**: Never commit `.env` files to version control. Add `.env` to your `.gitignore`.
---
### 4. Verify Installation
Test that CAI PRO is working correctly:
```bash
# Launch CAI CLI
cai
# Inside CAI, check your model
CAI> /model
# You should see:
# Available models:
# - alias1 (active) ✅
# - alias0
# - gpt-4o (requires OPENAI_API_KEY)
# - claude-sonnet-4 (requires ANTHROPIC_API_KEY)
# ...
```
**Expected output**: `alias1` should be listed and marked as active.
---
### 5. Run Your First Security Test
Let's start with a simple security assessment:
```bash
CAI> Analyze the security posture of https://testphp.vulnweb.com
# Alias1 will:
# 1. Perform reconnaissance
# 2. Identify vulnerabilities
# 3. Suggest exploitation techniques
# 4. Provide remediation guidance
```
**✅ Success!** You're now using unlimited alias1 tokens for security testing.
---
## Launch Terminal UI (TUI)
CAI PRO includes a powerful multi-terminal interface:
```bash
# Launch TUI mode
cai --tui
# Or set it as default in .env
echo "CAI_TUI_MODE=true" >> .env
cai
```
### TUI Quick Tips
**Keyboard Shortcuts:**
- `Ctrl+S` - Toggle sidebar
- `Ctrl+N` / `Ctrl+B` - Switch between terminals
- `Ctrl+L` - Clear terminal
- `Ctrl+Q` - Exit
**Add More Terminals:**
- Click the `[+]` button in the top bar
- Or use `/add` command
**Load Preconfigured Teams:**
- Open sidebar (`Ctrl+S`)
- Click "Teams" tab
- Select a team (e.g., "#1: 2 red + 2 bug")
[Full TUI Documentation →](tui/tui_index.md)
---
## Common First Tasks
### Task 1: Web Application Security Assessment
```bash
CAI> Conduct a comprehensive security assessment of https://example.com
# Alias1 will:
# - Enumerate subdomains and technologies
# - Identify OWASP Top 10 vulnerabilities
# - Test for SQL injection, XSS, CSRF
# - Generate a detailed report
```
### Task 2: CTF Challenge Solving
```bash
CAI> Solve this CTF challenge: [paste challenge description]
# Alias1 excels at:
# - Web challenges
# - Binary exploitation
# - Cryptography
# - Reverse engineering
```
### Task 3: Exploit Development
```bash
CAI> Write a Python exploit for CVE-2024-1234
# Alias1 will:
# - Research the vulnerability
# - Develop a working exploit
# - Include error handling
# - Add comments explaining each step
```
### Task 4: Bug Bounty Reconnaissance
```bash
CAI> Perform recon on https://bugbounty-target.com for a bug bounty program
# Alias1 will:
# - Enumerate attack surface
# - Identify interesting endpoints
# - Suggest testing strategies
# - Prioritize high-value targets
```
---
## Advanced Configuration
### Enable Context Monitoring
Track your token usage in real-time:
```bash
CAI> /context
# Shows:
# - Total tokens used/available
# - Breakdown by category (system, tools, memory, messages)
# - Visual grid representation
# - Optimization suggestions
```
### Multi-Agent Parallel Execution
Run multiple agents simultaneously in TUI:
```bash
# In TUI mode, open sidebar (Ctrl+S)
# Click "Teams" tab
# Select Team #1: "2 red + 2 bug"
# Type your prompt and press Ctrl+Shift+A to broadcast to all terminals
Scan target.com for vulnerabilities
```
### Save and Load Sessions
```bash
# Save your current conversation
CAI> /save pentest_session.json
# Load it later
CAI> /load pentest_session.json
```
---
## Troubleshooting
### Issue: "alias1 not available"
**Solution 1**: Check your API key
```bash
# Verify ALIAS_API_KEY is set correctly
env | grep ALIAS
```
**Solution 2**: Ensure you're using CAI PRO version
```bash
cai --version
# Should show v0.6.0 or higher
```
**Solution 3**: Contact support
- Email: support@aliasrobotics.com
- Subject: "alias1 not available - [your email]"
---
### Issue: "Rate limit exceeded"
**This shouldn't happen with CAI PRO** (unlimited tokens). If you see this:
1. Check for typos in your `ALIAS_API_KEY`
2. Contact support immediately: support@aliasrobotics.com
---
### Issue: TUI not launching
**Solution 1**: Install required dependencies
```bash
pip install textual rich
```
**Solution 2**: Check terminal compatibility
```bash
# TUI requires a modern terminal emulator
# Recommended: Alacritty, iTerm2, Windows Terminal
```
**Solution 3**: Use CLI mode instead
```bash
# TUI is optional, CLI works everywhere
cai # without --tui flag
```
---
## Next Steps
### 📚 Learn More
- **[TUI Full Guide](tui/tui_index.md)** - Master the Terminal UI
- **[Commands Reference](tui/commands_reference.md)** - All available commands
- **[Alias1 Deep Dive](cai_pro_alias1.md)** - Understand your flagship model
- **[Features Overview](cai_pro_features.md)** - Explore all CAI PRO capabilities
### 🎯 Practical Guides
- **[Running Agents](running_agents.md)** - Agent selection and configuration
- **[Context Management](context.md)** - Optimize token usage
- **[Guardrails & Security](guardrails.md)** - Secure testing practices
- **[Environment Variables](environment_variables.md)** - Complete configuration reference
### 🏆 Case Studies
Learn from real-world CAI applications:
- [Ecoforest Heat Pumps OT Security](https://aliasrobotics.com/case-studies-robot-cybersecurity.php)
- [MiR Robot Vulnerability Discovery](https://aliasrobotics.com/case-studies-robot-cybersecurity.php)
- [Mercado Libre API Testing](https://aliasrobotics.com/case-studies-robot-cybersecurity.php)
---
## Get Help
### Professional Support (CAI PRO Subscribers)
- **Email**: support@aliasrobotics.com (48h SLA)
- **Discord**: #pro-support channel (exclusive)
- **Quarterly Calls**: Strategy and roadmap discussions
### Community Resources
- **[Discord Community](https://discord.gg/fnUFcTaQAC)** - 1000+ security researchers
- **[GitHub Issues](https://github.com/aliasrobotics/cai/issues)** - Bug reports and feature requests
- **[Documentation](index.md)** - Complete CAI documentation
---
## Tips for Success
### 🎯 Best Practices
1. **Start with clear prompts**: Be specific about your testing scope and objectives
2. **Use context monitoring**: Check `/context` regularly to optimize token usage
3. **Leverage parallel execution**: Run multiple agents for comprehensive coverage
4. **Save your sessions**: Use `/save` to preserve important conversations
5. **Enable guardrails**: Keep `CAI_GUARDRAILS=true` for safer operations
### ⚡ Power User Tips
- **Keyboard shortcuts**: Master `Ctrl+N`, `Ctrl+B`, `Ctrl+S` for efficient TUI navigation
- **Team presets**: Use preconfigured teams instead of manual agent setup
- **Mix models**: Use alias1 for exploitation, GPT-4o for professional reporting
- **Custom agents**: Request specialized agents for your domain (contact support)
---
## Congratulations! 🎉
You're now ready to leverage CAI PRO for professional security testing.
**Remember:**
- ✅ Unlimited alias1 tokens
- ✅ Zero refusals for authorized testing
- ✅ Professional support available
- ✅ European data privacy guaranteed
**Questions?** Contact support@aliasrobotics.com
---
<small>
*Need help? We're here: **support@aliasrobotics.com***
*Want to upgrade to Enterprise? [Request quote →](mailto:contact@aliasrobotics.com?subject=CAI%20Enterprise%20Inquiry)*
</small>

1316
docs/cli/advanced_usage.md Normal file
View File

File diff suppressed because it is too large Load Diff

356
docs/cli/cli_index.md Normal file
View File

@ -0,0 +1,356 @@
# CAI Command Line Interface (CLI)
The CAI CLI provides a powerful, terminal-based interface for interacting with cybersecurity AI agents through a traditional command-line environment, optimized for automation, scripting, and integration workflows.
```
CCCCCCCCCCCCC ++++++++ ++++++++ IIIIIIIIII
CCC::::::::::::C ++++++++++ ++++++++++ I::::::::I
CC:::::::::::::::C ++++++++++ ++++++++++ I::::::::I
C:::::CCCCCCCC::::C +++++++++ ++ +++++++++ II::::::II
C:::::C CCCCCC +++++++ +++++ +++++++ I::::I
C:::::C +++++ +++++++ +++++ I::::I
C:::::C ++++ ++++ I::::I
C:::::C ++ ++ I::::I
C:::::C + +++++++++++++++ + I::::I
C:::::C +++++++++++++++++++ I::::I
C:::::C +++++++++++++++++ I::::I
C:::::C CCCCCC +++++++++++++++ I::::I
C:::::CCCCCCCC::::C +++++++++++++ II::::::II
CC:::::::::::::::C +++++++++ I::::::::I
CCC::::::::::::C +++++ I::::::::I
CCCCCCCCCCCCC ++ IIIIIIIIII
Cybersecurity AI (CAI), v0.6.0
Bug bounty-ready AI
CAI>
```
## Overview
The CLI is the foundational interface for CAI, offering:
- **⚡ Lightweight Execution**: Minimal resource overhead for maximum performance
- **🤖 Direct Agent Interaction**: Immediate access to all CAI agents
- **📝 Command System**: 30+ built-in commands for complete control
- **🔄 Automation Ready**: Perfect for scripting and CI/CD pipelines
- **🧩 Queue System**: Batch processing with command chaining
- **⚙️ Parallel Execution**: Run multiple agents simultaneously
- **💾 Session Management**: Save and restore conversations
- **🔧 Shell Integration**: Direct shell command execution
## When to Use the CLI vs TUI
| Feature | CLI | TUI |
|---------|-----|-----|
| **Scripting/Automation** | ✅ Full support | ❌ Interactive only |
| **CI/CD Integration** | ✅ Perfect fit | ❌ Not suitable |
| **Resource Usage** | ✅ Minimal | ⚠️ Higher (UI overhead) |
| **Batch Processing** | ✅ Queue system | ⚠️ Limited |
| **Visual Feedback** | ⚠️ Text-based | ✅ Rich UI |
| **Multi-agent Workflows** | ✅ Parallel mode | ✅ Visual split-screen |
| **Remote/Headless** | ✅ SSH friendly | ⚠️ Requires terminal UI |
| **Learning Curve** | ⚠️ Steeper | ✅ Intuitive |
**Use CLI for**: Automation, scripting, CI/CD, headless servers, SSH sessions, batch processing
**Use TUI for**: Interactive testing, visual multi-agent workflows, exploratory analysis, real-time monitoring
## Quick Start
Launch the CLI:
```bash
cai
```
With an initial prompt:
```bash
cai --prompt "scan 192.168.1.1 for open ports"
```
With YAML configuration:
```bash
cai --yaml agents.yaml
```
Basic workflow:
1. Launch CAI: `cai`
2. Configure API key in `.env` or environment
3. Select a model: `/model alias1`
4. Choose an agent: `/agent redteam_agent`
5. Type your prompt and press **Enter**
See the [Getting Started Guide](getting_started.md) for detailed instructions.
## Key Features
### 🎯 Command System
Over 30 built-in commands organized by category:
- **Agent Management**: `/agent`, `/parallel`, `/run`
- **Memory & History**: `/memory`, `/history`, `/compact`, `/flush`, `/load`, `/merge`
- **Environment & Config**: `/config`, `/env`, `/workspace`, `/virtualization`
- **Tools & Integration**: `/mcp`, `/platform`, `/shell`
- **Utilities**: `/model`, `/graph`, `/context`, `/cost`, `/help`
All commands support aliases for faster typing (e.g., `/a` for `/agent`, `/h` for `/help`).
Learn more: [Commands Reference](commands_reference.md)
### ⚡ Parallel Execution
Run multiple agents simultaneously:
```bash
# Configure parallel agents
/parallel add redteam_agent
/parallel add bug_bounter_agent
/parallel add blueteam_agent
# Execute on all agents
/parallel run "analyze target.com"
```
Or use YAML configuration:
```bash
cai --yaml agents.yaml --prompt "test application security"
```
Learn more: [Advanced Usage](advanced_usage.md)
### 💻 Shell Integration
Execute shell commands directly:
```bash
# Using /shell command
/shell nmap -sV 192.168.1.1
# Using $ shortcut
$ whoami
# Using /$ alias
/$ ls -la
```
### 💾 Session Management
Save and restore conversations:
```bash
# Save current session
/save pentest_session.json
# Save as Markdown report
/save findings_report.md
# Load previous session
/load pentest_session.json
```
### 🧠 Memory Management
Advanced memory features for long-term context:
```bash
# Enable episodic memory
CAI_MEMORY=episodic cai
# Save memory snapshot
/memory save "web app vulnerabilities found"
# List saved memories
/memory list
# Apply memory to current session
/memory apply mem_12345
```
## System Requirements
- **Python**: 3.9 or higher
- **Terminal**: Any modern terminal (bash, zsh, fish)
- **API Key**: Valid `ALIAS_API_KEY` (get one from [Alias Robotics](https://aliasrobotics.com))
- **Operating System**: Linux, macOS, Windows (WSL recommended)
### Supported Terminals
- ✅ bash (Linux/macOS/WSL)
- ✅ zsh (macOS/Linux)
- ✅ fish (Linux/macOS)
- ✅ PowerShell (Windows)
- ✅ SSH sessions
- ✅ tmux/screen
- ✅ CI/CD environments
## Architecture
```
CAI CLI
├── Core Components
│ ├── run_cai_cli - Main interactive loop
│ ├── AgentManager - Agent lifecycle management
│ ├── CommandRegistry - Command routing and execution
│ └── SessionRecorder - Session logging and persistence
├── Command System
│ ├── AgentCommand - Agent switching and management
│ ├── ParallelCommand - Multi-agent coordination
│ ├── MCPCommand - External tool integration
│ ├── ConfigCommand - Environment management
│ └── 25+ additional commands
└── Integration Layer
├── PromptToolkit - Input handling and completion
├── FuzzyCompleter - Intelligent autocompletion
├── QueueManager - Batch execution
└── ShellExecutor - Direct shell access
```
For technical details, see the [Architecture Overview](../cai_architecture.md).
## Common Use Cases
### 1. CTF Challenges
```bash
# Set up CTF environment
export CTF_NAME="hackableii"
export CTF_CHALLENGE="web_challenge"
export CAI_AGENT_TYPE="redteam_agent"
# Launch with auto-execution
cai --prompt "analyze the challenge and find the flag"
```
### 2. Bug Bounty Automation
```bash
# Configure bug bounty workflow
/agent bug_bounter_agent
/model alias1
# Execute reconnaissance
Perform full reconnaissance on bugcrowd.example.com
```
### 3. CI/CD Security Testing
```bash
#!/bin/bash
# security-check.sh
export CAI_MAX_TURNS=10
export CAI_PRICE_LIMIT=5.0
export CAI_TRACING=false
cai --prompt "scan $CI_TARGET for OWASP Top 10 vulnerabilities ; generate JSON report" > security-report.json
```
### 4. Parallel Reconnaissance
```bash
# agents.yaml
agents:
- name: subdomain_scanner
agent_type: redteam_agent
model: alias1
- name: port_scanner
agent_type: network_security_analyzer_agent
model: alias1
- name: vulnerability_checker
agent_type: bug_bounter_agent
model: alias1
# Execute
cai --yaml agents.yaml --prompt "full reconnaissance on target.com"
```
## Quick Reference
### Essential Commands
| Command | Description | Example |
|---------|-------------|---------|
| `/agent list` | List all agents | `/agent list` |
| `/agent <name>` | Switch agent | `/agent redteam_agent` |
| `/model <name>` | Change model | `/model alias1` |
| `/config` | View configuration | `/config` |
| `/help` | Show help | `/help agent` |
| `/save <file>` | Save session | `/save session.json` |
| `/load <file>` | Load session | `/load session.json` |
| `/cost` | Show costs | `/cost` |
### Keyboard Shortcuts
| Shortcut | Action |
|----------|--------|
| `Tab` | Autocomplete commands |
| `↑/↓` | Navigate command history |
| `Ctrl+C` | Interrupt execution |
| `Ctrl+L` | Clear screen |
| `Ctrl+D` | Exit CAI |
| `Ctrl+Z` | Suspend process |
| `Ctrl+X Ctrl+E` | Open editor |
See the complete [Commands Reference](commands_reference.md) for all commands.
## Configuration
CAI CLI can be configured via:
1. **Environment Variables**: `CAI_MODEL`, `CAI_AGENT_TYPE`, etc.
2. **`.env` File**: Place in your working directory
3. **`/config` Command**: Runtime configuration changes
4. **YAML Files**: Agent and workflow definitions
Example `.env`:
```env
ALIAS_API_KEY=ak_live_1234567890abcdef
CAI_MODEL=alias1
CAI_AGENT_TYPE=redteam_agent
CAI_DEBUG=1
CAI_PRICE_LIMIT=10.0
CAI_MAX_TURNS=50
```
For all configuration options, see [Configuration Guide](../getting-started/configuration.md).
## Documentation Structure
### For New Users
1. [Getting Started](getting_started.md) - First steps and basic usage
2. [Commands Reference](commands_reference.md) - Essential commands
### For Advanced Users
3. [Commands Reference](commands_reference.md) - Complete command list
4. [Advanced Usage](advanced_usage.md) - Automation, scripting, and advanced features
### Related Documentation
- [Configuration Guide](../getting-started/configuration.md) - All environment variables
- [Architecture Overview](../cai_architecture.md) - Technical architecture
- [TUI Documentation](../tui/tui_index.md) - Terminal UI alternative
## Community and Support
- **Documentation**: [https://docs.aliasrobotics.com](https://docs.aliasrobotics.com)
- **GitHub Issues**: [https://github.com/aliasrobotics/cai/issues](https://github.com/aliasrobotics/cai/issues)
- **Discord**: [Join our community](https://discord.gg/aliasrobotics)
- **Twitter**: [@aliasrobotics](https://twitter.com/aliasrobotics)
## What's Next?
- 📖 [Getting Started Guide](getting_started.md) - Learn the basics
- 📚 [Commands Reference](commands_reference.md) - Master all commands
- 🚀 [Advanced Usage](advanced_usage.md) - Unlock powerful features
---
*Last updated: November 2025 | CAI CLI v0.6+*

1291
docs/cli/commands_reference.md Normal file
View File

File diff suppressed because it is too large Load Diff

563
docs/cli/getting_started.md Normal file
View File

@ -0,0 +1,563 @@
# Getting Started with CAI CLI
This guide will walk you through launching the CAI CLI for the first time and performing your first security assessment using the command-line interface.
## Prerequisites
Before starting, ensure you have:
- ✅ CAI installed (see [Installation Guide](../cai_installation.md))
- ✅ Python 3.9+ installed
- ✅ A valid `ALIAS_API_KEY` from [Alias Robotics](https://aliasrobotics.com)
## Step 1: Launch the CLI
Open your terminal and run:
```bash
cai
```
You should see the CAI banner and prompt:
```
CCCCCCCCCCCCC ++++++++ ++++++++ IIIIIIIIII
CCC::::::::::::C ++++++++++ ++++++++++ I::::::::I
CC:::::::::::::::C ++++++++++ ++++++++++ I::::::::I
C:::::CCCCCCCC::::C +++++++++ ++ +++++++++ II::::::II
C:::::C CCCCCC +++++++ +++++ +++++++ I::::I
C:::::C +++++ +++++++ +++++ I::::I
C:::::C ++++ ++++ I::::I
C:::::C ++ ++ I::::I
C:::::C + +++++++++++++++ + I::::I
C:::::C +++++++++++++++++++ I::::I
C:::::C +++++++++++++++++ I::::I
C:::::C CCCCCC +++++++++++++++ I::::I
C:::::CCCCCCCC::::C +++++++++++++ II::::::II
CC:::::::::::::::C +++++++++ I::::::::I
CCC::::::::::::C +++++ I::::::::I
CCCCCCCCCCCCC ++ IIIIIIIIII
Cybersecurity AI (CAI), v0.6.0
Bug bounty-ready AI
CAI>
```
The navigation bar at the bottom displays important system information including your current model, agent, cost tracking, and session details.
## Step 2: Configure Your API Key
If your `ALIAS_API_KEY` is not configured, you'll see an authentication error. Configure it using one of these methods:
### Method 1: Using a `.env` file (Recommended)
Create a `.env` file in your working directory:
```env
ALIAS_API_KEY=ak_live_1234567890abcdef
CAI_MODEL=alias1
CAI_AGENT_TYPE=redteam_agent
CAI_DEBUG=1
CAI_PRICE_LIMIT=10.0
```
### Method 2: Environment Variables
Set it directly in your terminal:
```bash
export ALIAS_API_KEY="ak_live_1234567890abcdef"
cai
```
### Method 3: Runtime Configuration
After launching CAI, use the `/config` command:
```bash
CAI> /config CAI_MODEL=alias1
```
To view all current configuration:
```bash
CAI> /config
```
## Step 3: Select Your Model
CAI supports multiple AI models. For optimal performance and cost balance, we recommend `alias1`:
```bash
CAI> /model alias1
```
To see all available models:
```bash
CAI> /model-show
```
### Recommended Models
| Model | Provider | Best For | Cost |
|-------|----------|----------|------|
| `alias1` | Alias Robotics | **Recommended** - Balanced performance | Medium |
| `gpt-4o` | OpenAI | Complex reasoning and multi-modal | High |
| `claude-3-5-sonnet-20241022` | Anthropic | Fast responses with good quality | High |
| `o1-mini` | OpenAI | Reasoning tasks | Medium |
> **💡 Tip**: You can change models at any time without losing your conversation history.
## Step 4: Choose Your Agent
CAI provides specialized agents for different security tasks. Here's how to choose:
### Option 1: List All Available Agents
```bash
CAI> /agent list
```
This displays all agents with their descriptions and primary use cases.
### Option 2: Use the Selection Agent
If you're unsure which agent to use, start with the `selection_agent`:
```bash
CAI> /agent selection_agent
CAI> I need to test a web application for SQL injection
```
The agent will recommend the best agent for your task.
### Option 3: Choose Directly
If you know which agent you need:
```bash
CAI> /agent redteam_agent
```
### Common Agents and When to Use Them
| Agent | Purpose | When to Use |
|-------|---------|-------------|
| `redteam_agent` | Offensive security testing | Default for penetration testing |
| `bug_bounter_agent` | Bug bounty hunting | Finding high-value vulnerabilities in web apps |
| `blueteam_agent` | Defensive security analysis | Security posture assessment and hardening |
| `one_tool_agent` | Single-tool execution | Quick scans with specific tools |
| `dfir_agent` | Digital forensics and incident response | Log analysis and forensic investigation |
| `reverse_engineering_agent` | Binary analysis | Malware analysis, firmware reversing |
| `network_security_analyzer_agent` | Network security assessment | Network scanning and traffic analysis |
| `wifi_security_agent` | WiFi security testing | Wireless penetration testing |
| `selection_agent` | Agent recommendation | **When unsure which agent to use** |
> **💡 Pro Tip**: Start with `selection_agent` if you're new to CAI—it will guide you to the right agent for your task.
## Step 5: Start Your First Interaction
Now you're ready to interact with CAI! Simply type your prompt and press **Enter**.
### Example 1: Basic Network Reconnaissance
```bash
CAI> Scan 192.168.1.1 for open ports and services
```
The agent will:
- Process your request
- Select and execute appropriate tools (e.g., nmap)
- Display results in real-time
- Provide analysis and recommendations
### Example 2: Web Application Testing
```bash
CAI> /agent bug_bounter_agent
CAI> Test https://example.com for common web vulnerabilities
```
The agent will:
- Perform reconnaissance
- Test for OWASP Top 10 vulnerabilities
- Execute security tools
- Provide detailed findings
### Example 3: CTF Challenge
```bash
# Set up CTF environment
CAI> /config CTF_NAME=hackableii
CAI> /config CTF_CHALLENGE=web_challenge
# Start the challenge
CAI> Analyze this CTF challenge and find the flag
```
### Understanding the Output
As the agent works, you'll see:
1. **Tool Execution**: Messages showing which tools are being launched
2. **Tool Output**: Real-time results from executed commands
3. **Agent Reasoning**: The agent's thought process (if `CAI_DEBUG=1`)
4. **Final Analysis**: Summary, findings, and recommendations
5. **Cost Tracking**: Updated costs in the navigation bar
## Step 6: Essential Commands
Here are the most important commands to know:
### Getting Help
```bash
# General help
CAI> /help
# Help for specific command
CAI> /help agent
# Quick reference guide
CAI> /quickstart
```
### Agent Management
```bash
# List all agents
CAI> /agent list
# Switch to a specific agent
CAI> /agent redteam_agent
# Get info about current agent
CAI> /agent info
```
### Model Management
```bash
# View current model
CAI> /model
# Change model
CAI> /model gpt-4o
# List all available models
CAI> /model-show
```
### Session Management
```bash
# Save current conversation
CAI> /save pentest_session.json
# Save as Markdown report
CAI> /save findings_report.md
# Load previous conversation
CAI> /load pentest_session.json
```
### View History and Costs
```bash
# View conversation history
CAI> /history
# View last 20 messages
CAI> /history 20
# Check costs and token usage
CAI> /cost
```
### Clear and Reset
```bash
# Clear terminal output (keeps history)
CAI> Ctrl+L
# Flush conversation history
CAI> /flush
# Exit CAI
CAI> /exit
# or press Ctrl+D
```
## Step 7: Shell Command Execution
CAI allows you to execute shell commands directly:
### Using /shell Command
```bash
CAI> /shell nmap -sV 192.168.1.1
```
### Using $ Shortcut
```bash
CAI> $ whoami
CAI> $ ls -la
CAI> $ nmap -sV localhost
```
### Interactive Tools
For interactive tools, the agent will handle them appropriately:
```bash
CAI> Run a comprehensive port scan on 192.168.1.0/24
# Agent will execute nmap with appropriate flags
```
## Step 8: Working with Configuration
### View Current Configuration
```bash
CAI> /config
```
This displays a panel with all environment variables and their current values.
### Change Configuration at Runtime
```bash
# Set a specific variable (use the number from /config output)
CAI> /config set 18 "5.0"
# Or set by name
CAI> /config CAI_PRICE_LIMIT=5.0
CAI> /config CAI_MAX_TURNS=50
```
### Important Configuration Variables
| Variable | Description | Example |
|----------|-------------|---------|
| `CAI_MODEL` | Default model to use | `alias1` |
| `CAI_AGENT_TYPE` | Default agent | `redteam_agent` |
| `CAI_DEBUG` | Debug level (0-2) | `1` |
| `CAI_PRICE_LIMIT` | Maximum cost in USD | `10.0` |
| `CAI_MAX_TURNS` | Maximum conversation turns | `50` |
| `CAI_MAX_INTERACTIONS` | Maximum tool interactions | `100` |
| `CAI_TRACING` | Enable OpenTelemetry tracing | `true` |
| `CAI_GUARDRAILS` | Enable security guardrails | `true` |
See the complete [Configuration Guide](../cai/getting-started/configuration.md) for all options.
## Step 9: Common Workflows
### Workflow 1: Quick Security Scan
```bash
# Launch with specific agent
CAI_AGENT_TYPE=redteam_agent cai
# Execute scan
CAI> Perform a quick security assessment of 192.168.1.100
# Save results
CAI> /save quick_scan_results.md
```
### Workflow 2: Bug Bounty Reconnaissance
```bash
# Start with bug bounty agent
CAI> /agent bug_bounter_agent
# Reconnaissance
CAI> Perform full reconnaissance on target.com
# Test specific vulnerability
CAI> Test the login form for SQL injection
# Generate report
CAI> Generate a detailed bug bounty report
# Save session
CAI> /save bugbounty_target_session.json
```
### Workflow 3: CTF Challenge
```bash
# Configure CTF environment
export CTF_NAME="hackableii"
export CTF_CHALLENGE="web_app"
export CAI_AGENT_TYPE="redteam_agent"
# Launch and solve
cai
CAI> Analyze this CTF challenge and find the flag
```
### Workflow 4: Network Analysis
```bash
CAI> /agent network_security_analyzer_agent
# Analyze network
CAI> Scan the network 192.168.1.0/24 for security issues
# Analyze captured traffic
CAI> Analyze this PCAP file for suspicious activity
# View findings
CAI> /history
```
## Step 10: Keyboard Shortcuts
Master these shortcuts for faster navigation:
| Shortcut | Action |
|----------|--------|
| `Tab` | Autocomplete commands and arguments |
| `↑` / `↓` | Navigate through command history |
| `Ctrl+C` | Interrupt current execution |
| `Ctrl+L` | Clear terminal screen |
| `Ctrl+Z` | Suspend process (resume with `fg`) |
| `Ctrl+U` | Clear current input line |
| `Ctrl+A` | Move cursor to start of line |
| `Ctrl+E` | Move cursor to end of line |
## Common First-Time Issues
### Issue: API Key Not Valid
**Solution**:
```bash
# Check your API key is set correctly
CAI> /env | grep ALIAS_API_KEY
# If not set, add it to .env file
echo "ALIAS_API_KEY=your_key_here" >> .env
```
### Issue: Agent Not Responding
**Solution**:
```bash
# Cancel current operation
Ctrl+C
# Check agent is loaded
CAI> /agent
# Switch to a different agent
CAI> /agent redteam_agent
```
### Issue: Command Not Found
**Solution**:
```bash
# Get help for available commands
CAI> /help
# Use Tab completion to see available commands
CAI> /<Tab>
# Check command syntax
CAI> /help <command_name>
```
### Issue: Price Limit Reached
**Solution**:
```bash
# Check current costs
CAI> /cost
# Increase limit
CAI> /config CAI_PRICE_LIMIT=20.0
# Or set it before launching
CAI_PRICE_LIMIT=20.0 cai
```
### Issue: Max Turns Exceeded
**Solution**:
```bash
# Increase turn limit
CAI> /config CAI_MAX_TURNS=100
# Or flush history and start fresh
CAI> /flush
```
## Next Steps
Congratulations! You've completed the basics of CAI CLI. Here's what to explore next:
### Learn More Commands
- 📚 [Commands Reference](commands_reference.md) - Complete command documentation
- 🚀 [Advanced Usage](advanced_usage.md) - Automation, scripting, and advanced features
### Explore Advanced Features
- **Queue System**: Batch process multiple prompts
- **Parallel Execution**: Run multiple agents simultaneously
- **Memory Management**: Persistent context across sessions
- **MCP Integration**: Connect external tools and services
### Specialized Workflows
- **CTF Challenges**: Learn CTF-specific workflows
- **Bug Bounty**: Master bug bounty hunting techniques
- **Automation**: Script security assessments
- **CI/CD Integration**: Integrate CAI into your pipeline
### Get Help
- ❓ [FAQ](../cai_faq.md) - Common questions
- 💬 [Discord](https://discord.gg/aliasrobotics) - Community support
- 🐛 [GitHub Issues](https://github.com/aliasrobotics/cai/issues) - Report bugs
## Quick Reference Card
### Most Used Commands
```bash
/agent list # List all agents
/agent <name> # Switch agent
/model <name> # Change model
/config # View configuration
/help # Get help
/save <file> # Save session
/load <file> # Load session
/cost # Show costs
/history # View history
/shell <cmd> # Run shell command
$ <cmd> # Shell shortcut
/exit # Exit CAI
```
### Essential Workflows
```bash
# Quick scan
cai --prompt "scan target.com for vulnerabilities"
# CTF mode
CTF_NAME="challenge" cai
# Bug bounty
CAI_AGENT_TYPE=bug_bounter_agent cai
# With initial setup
CAI_MODEL=alias1 CAI_PRICE_LIMIT=10 cai
```
---
*Last updated: November 2025 | CAI CLI v0.6+*

103
docs/stylesheets/extra.css
View File

@ -514,3 +514,106 @@
grid-template-columns: 1fr;
}
}
/* ====================
Enhanced Navigation Styling - Refined & Professional
Only affects left sidebar navigation, not TOC
==================== */
/* Target ONLY the primary (left) sidebar navigation */
.md-sidebar--primary .md-sidebar__scrollwrap {
/* Main navigation sections - subtle but clear hierarchy */
}
/* Main sections (Getting Started, CAI PRO, User Interfaces, etc.) */
.md-sidebar--primary .md-nav--primary > .md-nav__list > .md-nav__item > .md-nav__link {
color: #529d86 !important;
font-weight: 600 !important;
font-size: 0.75rem !important;
text-transform: uppercase;
letter-spacing: 0.03em;
padding-top: 0.6rem !important;
padding-bottom: 0.4rem !important;
margin-top: 0.3rem;
border-left: 2px solid transparent;
transition: all 0.15s ease;
}
/* Hover effect for main sections - subtle */
.md-sidebar--primary .md-nav--primary > .md-nav__list > .md-nav__item > .md-nav__link:hover {
border-left-color: #529d86;
background-color: rgba(82, 157, 134, 0.04);
}
/* Active main section - slightly more visible */
.md-sidebar--primary .md-nav--primary > .md-nav__list > .md-nav__item > .md-nav__link--active {
color: #428072 !important;
border-left-color: #529d86;
background-color: rgba(82, 157, 134, 0.06);
font-weight: 700 !important;
}
/* Subsections (TUI, CLI, etc.) - keep normal weight */
.md-sidebar--primary .md-nav__item--nested > .md-nav__link {
font-size: 0.7rem !important;
font-weight: 500 !important;
}
/* Regular links - no changes to size */
.md-sidebar--primary .md-nav__link {
font-size: 0.7rem;
}
/* Active page in navigation - green highlight */
.md-sidebar--primary .md-nav__link--active {
color: #529d86 !important;
font-weight: 500;
}
/* Spacing between sections - subtle */
.md-sidebar--primary .md-nav--primary > .md-nav__list > .md-nav__item {
margin-bottom: 0.2rem;
}
/* Special styling for CAI PRO section - very subtle gradient */
.md-sidebar--primary .md-nav__item > .md-nav__link[title*="CAI PRO"],
.md-sidebar--primary .md-nav__item > .md-nav__link[title*="🚀"] {
background: linear-gradient(90deg, rgba(82, 157, 134, 0.05) 0%, rgba(82, 157, 134, 0.01) 100%);
border-left-width: 3px;
}
/* Table of Contents (right sidebar) - Apply color scheme, keep sizes */
.md-sidebar--secondary .md-nav__link {
font-size: inherit !important;
text-transform: none !important;
transition: color 0.15s ease;
}
/* TOC - Main headings (h1, h2) with green color */
.md-sidebar--secondary .md-nav__list > .md-nav__item > .md-nav__link {
color: #529d86 !important;
font-weight: 600 !important;
}
/* TOC - Sub-headings (h3, h4) with darker gray */
.md-sidebar--secondary .md-nav__list .md-nav__item .md-nav__item > .md-nav__link {
color: #5a5a5a !important;
font-weight: 500 !important;
}
/* TOC - Hover effect */
.md-sidebar--secondary .md-nav__link:hover {
color: #428072 !important;
}
/* TOC - Active/current section */
.md-sidebar--secondary .md-nav__link--active {
color: #529d86 !important;
font-weight: 700 !important;
}
/* Smooth transitions for better UX */
.md-sidebar--primary .md-nav__link,
.md-sidebar--secondary .md-nav__link {
transition: color 0.15s ease, background-color 0.15s ease, border-color 0.15s ease;
}

114
mkdocs.yml
View File

@ -23,18 +23,52 @@ theme:
repo_url: https://github.com/aliasrobotics/cai
repo_name: aliasrobotics/cai
nav:
# ========================================
# GETTING STARTED (Simplificado)
# ========================================
- Getting Started:
- Welcome: index.md
- Installation: cai_installation.md
- Quickstart: cai_quickstart.md
- Available Models: cai_list_of_models.md
- Model Providers:
- OpenRouter: providers/openrouter.md
- Ollama: providers/ollama.md
- Azure OpenAI: providers/azure.md
- '🚀 CAI PRO': cai_pro.md
# ========================================
# CAI PRO (EXPANDIDO - COMERCIAL) ⭐
# ========================================
- '🚀 CAI PRO - Professional Edition':
- Why CAI PRO?: cai_pro.md
- Alias1 Model: cai_pro_alias1.md
- Exclusive Features: cai_pro_features.md
- Pricing & Plans: cai_pro_pricing.md
- Get Started with PRO: cai_pro_quickstart.md
- Contact Sales: cai_pro_contact.md
# ========================================
# USER INTERFACES (NUEVO AGRUPAMIENTO)
# ========================================
- User Interfaces:
# Terminal UI (TUI) - Subsección
- Terminal UI (TUI):
- Overview: tui/tui_index.md
- Getting Started: tui/getting_started.md
- User Interface: tui/user_interface.md
- Terminals Management: tui/terminals_management.md
- Teams & Parallel Execution: tui/teams_and_parallel_execution.md
- Sidebar Features: tui/sidebar_features.md
- Keyboard Shortcuts: tui/keyboard_shortcuts.md
- Commands Reference: tui/commands_reference.md
- Advanced Features: tui/advanced_features.md
- Troubleshooting: tui/troubleshooting.md
# Command Line Interface (CLI) - Subsección
- Command Line Interface (CLI):
- Overview: cli/cli_index.md
- Getting Started: cli/getting_started.md
- Commands Reference: cli/commands_reference.md
- Advanced Usage: cli/advanced_usage.md
# ========================================
# CORE CONCEPTS
# ========================================
- Core Concepts:
- Architecture: cai_architecture.md
- Agents: agents.md
@ -42,15 +76,21 @@ nav:
- Handoffs: handoffs.md
- Multi-Agent Systems: multi_agent.md
- Benchmarking:
- Overview: benchmarking/overview.md
- Running Benchmarks: benchmarking/running_benchmarks.md
- Attack & Defense CTFs: benchmarking/attack_defense.md
- Jeopardy CTFs: benchmarking/jeopardy_ctfs.md
- Cyber Ranges: benchmarking/cyber_ranges.md
- Knowledge Benchmarks: benchmarking/knowledge_benchmarks.md
- Privacy Benchmarks: benchmarking/privacy_benchmarks.md
# ========================================
# MODELS & PROVIDERS (REORGANIZADO)
# ========================================
- Models & Providers:
# TODO: Crear página destacada para Alias Models
# - '⭐ Alias Models (CAI PRO)': cai_alias_models.md
- Available Models: cai_list_of_models.md
- Model Providers:
- OpenRouter: providers/openrouter.md
- Ollama: providers/ollama.md
- Azure OpenAI: providers/azure.md
# ========================================
# GUIDES
# ========================================
- Guides:
- Running Agents: running_agents.md
- Working with Results: results.md
@ -60,18 +100,29 @@ nav:
- Guardrails & Security: guardrails.md
- Environment Variables: environment_variables.md
- Terminal UI (TUI):
- Overview: tui/tui_index.md
- Getting Started: tui/getting_started.md
- User Interface: tui/user_interface.md
- Terminals Management: tui/terminals_management.md
- Teams & Parallel Execution: tui/teams_and_parallel_execution.md
- Sidebar Features: tui/sidebar_features.md
- Keyboard Shortcuts: tui/keyboard_shortcuts.md
- Commands Reference: tui/commands_reference.md
- Advanced Features: tui/advanced_features.md
- Troubleshooting: tui/troubleshooting.md
# ========================================
# BENCHMARKING (CREDIBILIDAD)
# ========================================
- Benchmarking:
- Overview: benchmarking/overview.md
- Running Benchmarks: benchmarking/running_benchmarks.md
- Attack & Defense CTFs: benchmarking/attack_defense.md
- Jeopardy CTFs: benchmarking/jeopardy_ctfs.md
- Cyber Ranges: benchmarking/cyber_ranges.md
- Knowledge Benchmarks: benchmarking/knowledge_benchmarks.md
- Privacy Benchmarks: benchmarking/privacy_benchmarks.md
# ========================================
# RESEARCH (CREDIBILIDAD CIENTÍFICA)
# ========================================
- Research:
- Overview: research.md
# TODO: Opcional - expandir research
# - Publications: research_publications.md
# ========================================
# API REFERENCE (TÉCNICO)
# ========================================
- API Reference:
- Agents:
- Agent: ref/agent.md
@ -97,13 +148,15 @@ nav:
- Handoff Filters: ref/extensions/handoff_filters.md
- Handoff Prompt: ref/extensions/handoff_prompt.md
# ========================================
# ADVANCED
# ========================================
- Advanced:
# - Benchmarks: cai_benchmark.md
- Development: cai_development.md
- Research:
- Overview: research.md
# ========================================
# RESOURCES
# ========================================
- Resources:
- FAQ: cai_faq.md
- Find Us: cai_find_us.md
@ -115,9 +168,8 @@ plugins:
handlers:
python:
paths: ["src"]
selection:
docstring_style: google
options:
docstring_style: google
# Shows links to other members in signatures
signature_crossrefs: true
# Orders members by source order, rather than alphabetical