concierge
Verified Safeby Agentic-Web-Interfaces
Overview
A declarative framework for building agentic AI services, enabling Large Language Models (LLMs) to interact with and navigate through complex web application workflows by defining tasks, stages, and transitions.
Installation
concierge serve --config your_workflow.yamlEnvironment Variables
- OPENAI_API_KEY
- DB_HOST
- DB_PORT
- DB_NAME
- DB_USER
- DB_PASSWORD
Security Notes
The FastAPI server enables permissive CORS (`allow_origins=["*"]`) by default, which is a security risk in production environments if not restricted. The default database configuration in `configs/default.yaml` uses an empty password, which is insecure for production deployment. The system relies on LLM output being structured JSON, which helps mitigate direct code injection, and task execution is confined to predefined Python functions. No 'eval' or malicious code patterns were observed.
Similar Servers
MaxKB
An enterprise-grade intelligent agent platform for building knowledge bases, RAG, complex workflows, and AI agents, targeting intelligent customer service and office assistants.
trigger.dev
Local development and AI agent interface for Trigger.dev workflows, enabling Python script execution and managing tasks, runs, and deployments.
npcpy
A comprehensive Python library and framework for building, evaluating, and serving LLM-powered agents and multi-agent systems, integrating fine-tuning capabilities, knowledge graphs, and scalable model operations, with a built-in Flask API server for deployment.
agents
The Inkeep Agents project is a comprehensive framework and SDK for building, managing, and running AI agents. This specific 'MCP Server' component (integrated within the Management API) provides a machine-readable API for managing agent configurations, tools, data components, and other project resources.