Skip to content

SynthOrg Documentation

Framework for building synthetic organizations -- autonomous AI agents orchestrated as a virtual company.

SynthOrg lets you define agents with roles, hierarchy, budgets, and tools, then orchestrate them to collaborate on complex tasks as a virtual organization.

Under Active Development

SynthOrg is under active development. Many features described in the design specification are planned but not yet implemented. See the Roadmap for current status.

Get Started

  • Use SynthOrg

    Pick a template and run your first synthetic org via Docker.

    User Guide

  • Develop SynthOrg

    Clone the repo, set up your dev environment, and contribute.

    Developer Setup

  • Guides

    In-depth guides for configuration, agents, budgets, security, deployment, and more.

    Guides

Design Specification

The design spec covers the full architecture of SynthOrg -- from agent identity to budget enforcement:

  • Design Overview

    Vision, principles, core concepts, and glossary.

    Design Overview

  • Agents & HR

    Agent identity, roles, hiring, performance tracking, promotions.

    Agents

  • Organization & Templates

    Company types, hierarchy, departments, template system.

    Organization

  • Communication

    Message bus, delegation, conflict resolution, meeting protocols.

    Communication

  • Task & Workflow Engine

    Task lifecycle, execution loops, routing, recovery, shutdown.

    Engine

  • Memory & Persistence

    Memory types, backends, retrieval pipeline, operational data.

    Memory

  • Operations

    LLM providers, budget, tools, security, human interaction.

    Operations

Key Features

  • Agent Orchestration -- Define agents with roles, models, and tools. The engine handles task decomposition, routing, and collaboration.
  • Budget Enforcement -- Per-agent cost limits, auto-downgrade to cheaper models, spending reports, and CFO-level cost optimization.
  • Security & Trust -- SecOps agent, fail-closed rule engine, progressive trust (4 strategies), autonomy levels, and audit logging.
  • Memory -- Per-agent and shared organizational memory with retrieval pipeline, consolidation, and archival.
  • Communication -- Message bus, delegation, conflict resolution (4 strategies), and meeting protocols.
  • HR Engine -- Hiring, firing, onboarding, offboarding, performance tracking, and promotion criteria.
  • Tool Integration -- Built-in tools (file system, git, sandbox, code runner) plus MCP bridge for external tools.
  • LLM Providers -- Provider-agnostic via LiteLLM. Routing strategies, retry/rate-limiting, capability matching.

Further Reading

Section Description
Architecture System overview, module map, design principles
Tech Stack Technology choices and engineering conventions
Decision Log All design decisions, organized by domain
API Reference REST API reference (Scalar/OpenAPI)
Library Reference Auto-generated from docstrings
Roadmap Status, open questions, future vision
  • GitHub Repository
  • License (BSL 1.1, source available -- free production use for non-competing small orgs; converts to Apache 2.0 three years after release)
  • Licensing & Usage -- what's permitted, why BSL, and how to get a commercial license