2ly
Verified Safeby AlpinAI
Overview
2LY provides an infrastructure layer for AI agent tooling, enabling a private tool registry with embedded runtimes that integrate with various agent frameworks like LangChain, CrewAI, and AutoGPT.
Installation
docker compose up -dEnvironment Variables
- NATS_SERVERS
- DGRAPH_URL
- ENCRYPTION_KEY
- JWT_PRIVATE_KEY_PATH
- JWT_PUBLIC_KEY_PATH
- SYSTEM_KEY
- WORKSPACE_KEY
- SKILL_KEY
- RUNTIME_KEY
- RUNTIME_NAME
- SKILL_NAME
- REMOTE_PORT
- ROOTS
- CORS_ORIGINS
- LOG_LEVEL
- LOG_LEVELS
- PASSWORD_MIN_LENGTH
- JWT_ISSUER
- JWT_ACCESS_TOKEN_TTL
- JWT_REFRESH_TOKEN_TTL
- DEFAULT_OLLAMA_BASE_URL
Security Notes
The project demonstrates strong security practices for authentication and authorization, including RSA-based JWTs with token refreshing and database-validated workspace access to prevent stale privileges. It uses robust password hashing (scrypt with peppering via `ENCRYPTION_KEY`) and encrypts sensitive AI provider API keys in the database. Rate limiting is implemented for API key validation, and authentication errors are masked to prevent enumeration attacks. Cryptographic keys are auto-generated with secure file permissions during setup, and explicit warnings are provided against committing them to version control. GraphQL directives enforce granular access control. Future improvements noted in the codebase include full account lockout mechanisms, advanced password policies, and more comprehensive XSS/CSRF protections.
Similar Servers
trigger.dev
Local development and AI agent interface for Trigger.dev workflows, enabling Python script execution and managing tasks, runs, and deployments.
arcade-mcp
A framework and collection of toolkits for building and deploying AI agent servers that integrate with various external services.
mcp_massive
An AI agent orchestration server, likely interacting with LLMs and managing multi-agent workflows.
AgentUp
AgentUp is an infrastructure framework for developing, deploying, and managing production-ready AI agents, providing Docker-like consistency, security, and extensibility.