OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Orloj

Orloj is a Go-based open-source orchestration runtime and declarative stack for building and operating multi-agent AI systems. It represents agents, tools, models, memory, schedules, policies, approvals, workers and deployment resources as configurable infrastructure, then provides scheduling, execution, routing, governance and observability capabilities around them.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Orloj — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Orloj when an agent project needs operational controls beyond a prompt-and-loop script, including versioned manifests, task scheduling, worker ownership, model and tool routing, approvals, retries or traces.

Who it is for

  • Developers building multi-agent AI systems
  • Platform or operations teams managing agent workflows
  • Teams that need declarative configuration, permissions, approvals, retries and runtime visibility

Documented uses

  • Define agents, tools, models, memory and workflows as YAML resources
  • Schedule and route tasks across agent systems and workers
  • Apply tool permissions, roles, policies and human approval gates
  • Connect external services through HTTP, gRPC, webhooks, MCP, CLI, WASM and A2A integration paths
  • Inspect traces, logs, task history, messages, events and metrics
Before you choose

Requirements & limits

The repository is public, identifies an Apache-2.0 license and documents CLI, server and self-hosted operation paths. It states that the project is under active development and that APIs and resource schemas may change before 1.0.

  • Go-based runtime with YAML resource configuration
  • Supports local embedded-worker operation and documented paths toward Postgres, NATS JetStream and distributed workers
  • Offers both governance resources and operational observability
  • Provides multiple interfaces, including CLI, REST API, SDKs, Kubernetes CRDs and web console
  • The project is pre-1.0 and its APIs and resource schemas may change

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Define an Orloj agent system in YAML

Create the declarative resources for an agent system, its tools, models, memory and policies.

Before you start

  • Orloj source repository or runtime access
  • YAML manifests
  • Definitions for the agents, tools, model endpoints, memory, tasks and policy resources required by the system

Steps

  1. Write YAML resources for the agents, systems, tools, model endpoints, memory, tasks, secrets, evaluations and policies used by the system.

  2. Configure the relevant execution contracts, graph topology, roles, runtime bounds, provider routing or fallback models, and token budgets.

  3. Declare tool permissions, tool approvals or task approvals where governed execution is required.

  4. Use the documented Orloj interfaces, including manifests, the CLI, REST API, SDKs, Kubernetes CRDs or web console, to operate the declared resources.

Expected outcome

A versioned declarative definition of an agent system with its operational and governance resources.

Guide limitations

  • The repository states that Orloj is under active development and that APIs and resource schemas may change before 1.0.
  • This recipe describes configuration and operation stages documented by the repository; it does not establish a successful deployment or run.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
OrlojHQ/orloj · Official homepage title · retained in its source language
How we review sourcesSuggest a correction