-
Notifications
You must be signed in to change notification settings - Fork 4
FAQ
Frequently asked questions about aistack.
aistack is a production-grade multi-agent orchestration framework for Claude Code with adversarial validation, persistent memory, and real-time web dashboard.
- 11 specialized agent types
- 36 MCP tools
- SQLite + FTS5 + vector search
- Adversarial review loops
- Web dashboard
- 6 LLM providers
Yes, aistack is MIT licensed and free to use. However, you'll need API keys for LLM providers (Anthropic, OpenAI) unless you use Ollama (local).
- Node.js 20+
- Claude Code
- API key (Anthropic, OpenAI, or Ollama)
See Installation.
Use environment variables:
export ANTHROPIC_API_KEY="sk-..."
export OPENAI_API_KEY="sk-..."See Configuration Guide.
Default is 10, configurable via agents.maxConcurrent in config.
Yes! See Custom Agent Types.
See Agent Overview for selection guide.
SQLite database at ./data/aistack.db (configurable).
Optional semantic search using OpenAI or Ollama embeddings. See Vector Search Setup.
Yes, with Ollama for local LLM and local vector search.
claude mcp add aistack -- npx @blackms/aistack mcp startSee MCP Integration.
Yes, via CLI or programmatic API. See Programmatic API.
Check configuration file exists and is valid. See Troubleshooting.
Close other connections or increase timeout. See Troubleshooting.
Reduce concurrent agents or upgrade API tier.
Yes, but consider:
- API costs
- Database backups
- Security (no encryption at rest)
- Authentication setup
Yes, via CLI or programmatic API, but MCP integration requires MCP-compatible client.
See Contributing Guide.
Still have questions?
Getting Started
Core Concepts
Agent Guides
- Overview
- Coder
- Researcher
- Tester
- Reviewer
- Adversarial
- Architect
- Coordinator
- Analyst
- DevOps
- Documentation
- Security Auditor
MCP Tools
- Overview
- Agent Tools
- Memory Tools
- Task Tools
- Session Tools
- System Tools
- GitHub Tools
- Review Loop Tools
- Identity Tools
Recipes
- Index
- Code Review
- Doc Sync
- Multi-Agent
- Adversarial Testing
- Full-Stack Feature
- Memory Patterns
- GitHub Integration
Advanced
- Plugin Development
- Custom Agent Types
- Workflow Engine
- Vector Search Setup
- Web Dashboard
- Programmatic API
- Resource Monitoring
Reference