Orloj

data-ai MCP Server

An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.

data-aidata-ai
4 views104 stars9 forksApache-2.0

Why This Matters

Discovered via unknown and last synced 3mo ago.

Source
unknown
Stars
104
Last synced
3mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
25
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (25)

Language

Install

Python

`pip install orloj-sdk`

Memory

Vector-backed retrieval for agents

McpServer

MCP server connection that discovers/syncs MCP tools

TaskSchedule

Cron-based task creation

TaskWebhook

Event-triggered task creation

Agent

Unit of work backed by a language model

AgentSystem

Directed graph composing multiple agents

ModelEndpoint

Connection to a model provider

AgentRole

Named permission set bound to agents

ToolPermission

Required permissions for tool invocation

ToolApproval

Approval record for gated tool invocations

TypeScript

`npm install orloj`

Worker

Execution unit with capability declaration

Resource

Purpose

Secret

Credential storage

AgentPolicy

Token, model, and tool constraints

Task

Request to execute an AgentSystem

Tool

External capability with isolation and retry

orlojworker

Claims tasks, renews leases, executes agent graphs, consumes message-driven inboxes, routes models, invokes tools, and reports status.

orlojctl

Applies manifests, scaffolds systems, creates secrets, runs tasks, watches resources, reviews approvals, inspects logs, traces, graphs, messages, and metrics.

Layer

Resources and Runtime Behavior

Component

Responsibility

orlojd

Runs the REST API, web console, resource stores, watch/event endpoints, controllers, schedulers, and optional embedded worker.

Examples

Resource samples, blueprints, and use-case bundles.