Architecture Overview
Understanding how Bootspring works under the hood.
System Architecture
Bootspring is a multi-component system that provides AI-assisted development tools:
┌─────────────────────────────────────────────────────────────────────┐
│ CLIENT LAYER │
├─────────────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ CLI │ │ Claude │ │ VS Code │ │Dashboard │ │
│ │ │ │ Desktop │ │Extension │ │ (Web) │ │
│ └────┬─────┘ └────┬─────┘ └────┬─────┘ └────┬─────┘ │
│ │ │ │ │ │
└────────┼───────────────┼───────────────┼───────────────┼──────────┘
│ │ │ │
│ │ MCP Protocol │ │
▼ ▼ ▼ ▼
┌─────────────────────────────────────────────────────────────────────┐
│ MCP SERVER │
├─────────────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────────────────────────────────────────────────────┐ │
│ │ Tool Registry │ │
│ │ assist | context | agent | skill | workflow | ... │ │
│ └──────────────────────────────────────────────────────────┘ │
│ │ │
│ ┌──────────────────────────┼──────────────────────────────┐ │
│ │ ▼ │ │
│ │ ┌────────────┐ ┌────────────┐ ┌────────────┐ │ │
│ │ │ Agent │ │ Skill │ │ Workflow │ │ │
│ │ │ Engine │ │ Engine │ │ Engine │ │ │
│ │ └────────────┘ └────────────┘ └────────────┘ │ │
│ │ Core Engines │ │
│ └──────────────────────────────────────────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────────┘
│ │
│ Local │ Remote
▼ ▼
┌─────────────────────────┐ ┌─────────────────────────┐
│ Local Storage │ │ Bootspring API │
├─────────────────────────┤ ├─────────────────────────┤
│ │ │ │
│ .bootspring/ │ │ Authentication │
│ context/ │ │ Usage Tracking │
│ agents/ │ │ License Validation │
│ skills/ │ │ Cloud Sync │
│ config.json │ │ │
│ │ │ │
└─────────────────────────┘ └─────────────────────────┘
Core Components
Client Layer
End-user interfaces:
| Component | Description |
|---|---|
| CLI | Command-line tool for direct interaction |
| Claude Desktop | MCP integration for Claude |
| VS Code Extension | IDE integration |
| Dashboard | Web-based management |
MCP Server
The Model Context Protocol server:
- Exposes tools to AI assistants
- Manages local state
- Orchestrates workflows
- Communicates with APIs
Core Engines
Business logic components:
| Engine | Purpose |
|---|---|
| Agent Engine | Manages expert agent invocations |
| Skill Engine | Handles pattern application |
| Workflow Engine | Orchestrates multi-phase processes |
| Context Engine | Generates and manages context |
| Quality Engine | Runs quality gates |
Data Flow
Agent Invocation Flow
User → CLI/MCP → Agent Engine → Context Assembly → LLM → Response → User
- User requests agent invocation
- CLI/MCP receives request
- Agent engine loads agent profile
- Context engine assembles relevant context
- Request sent to LLM
- Response processed and returned
Context Generation Flow
Codebase → Analyzers → Aggregator → Template → CLAUDE.md
- File system scanned
- Multiple analyzers extract information
- Results aggregated
- Template applied
- Context file generated
Workflow Orchestration
Workflow Definition → Phase Manager → Agent Coordination → Completion Signals
- Workflow loaded from definition
- Phase manager tracks progress
- Agents invoked for each phase
- Completion signals validate progress
Architecture Docs
| Document | Description |
|---|---|
| Bootspring Internals | Core system design |
| MCP Protocol | MCP implementation details |
| Context System | Context generation |
| Agent System | Agent architecture |
| Workflow Engine | Workflow orchestration |
| Plugin System | Extension architecture |
Design Principles
1. Local-First
Bootspring operates primarily locally:
- No data leaves your machine without consent
- Works offline for most features
- API calls only for auth/tracking
2. Protocol-Based
Uses standard protocols:
- MCP for AI integration
- REST for API
- JSON for configuration
- Git for version control
3. Extensible
Built for extension:
- Plugin architecture
- Custom agents
- Custom skills
- Custom workflows
4. Non-Invasive
Doesn't modify your code unless asked:
- Generates context files
- Suggests changes via AI
- Never auto-commits
Technology Stack
CLI & MCP Server
| Technology | Purpose |
|---|---|
| Node.js | Runtime |
| TypeScript | Language |
| Commander.js | CLI framework |
| MCP SDK | Protocol implementation |
API & Dashboard
| Technology | Purpose |
|---|---|
| Next.js | Web framework |
| PostgreSQL | Database |
| Prisma | ORM |
| JWT Sessions | Authentication |
| Stripe | Payments |
| Vercel | Hosting |
AI Integration
| Technology | Purpose |
|---|---|
| Claude 3.5 | Primary AI model |
| OpenAI (optional) | Alternative provider |
| LangChain (internal) | LLM orchestration |
Deployment Architecture
Local Installation
User Machine
├── bootspring (CLI)
├── .bootspring/
│ ├── config.json
│ ├── context/
│ └── cache/
└── Your Project
├── CLAUDE.md
└── bootspring.config.js
Cloud Services
┌─────────────────┐
│ Vercel CDN │
└────────┬────────┘
│
┌──────────────┼──────────────┐
│ │ │
▼ ▼ ▼
┌──────────┐ ┌──────────┐ ┌──────────┐
│ Dashboard │ │ API │ │ Webhooks │
│ (Next.js)│ │ (Next.js)│ │ Handlers │
└─────┬─────┘ └─────┬────┘ └─────┬────┘
│ │ │
└──────────────┼──────────────┘
│
┌──────────────┼──────────────┐
│ │ │
▼ ▼ ▼
┌──────────┐ ┌──────────┐ ┌──────────┐
│PostgreSQL│ │ Redis │ │ S3 │
│ (Neon) │ │(Upstash) │ │(Backups) │
└──────────┘ └──────────┘ └──────────┘
Security Architecture
Authentication Flow
User → Sign-in Route → JWT Cookie → API → Resource
API Key Security
- Keys hashed with bcrypt
- Scoped permissions
- Audit logging
- Rate limiting
Data Protection
- TLS in transit
- Encrypted at rest
- No code stored server-side
- GDPR compliant