Meridian OS: Open-source company OS for human and AI agent teams

Repositorycodejunkie99/meridian-company-osTool

Meridian OS is an open-source control plane designed to manage hybrid organisations of human staff and AI agents. It integrates task tracking, goal alignment, token budgets, and governance into a unified web console.

Key points

  1. Operational control plane: Combines command dashboards, organigrams, risk monitors, and live heartbeat feeds.
  2. Built-in governance: Includes an approval inbox with policy checks for spend, hiring, publishing, and override decisions.
  3. Auditability and tracking: Features an immutable activity log with JSON export, tool-call traces, and automated CEO briefs.
  4. Autonomous simulation engine: Ticks every ~2.6 seconds to emulate agent heartbeats, task progress, and token burn without a connected runtime.
  5. Kimi Space: Agent chat interface supporting OS commands for task assignment, skill installation, and routing to local Kimi instances.

Why it matters

While agent orchestration tools manage execution, businesses require visibility into ownership, budgets, governance, and audit trails. Meridian OS attempts to bridge technical agent coordination with operational corporate management.

Analysis

Built with React 19 and strict TypeScript under the MIT license, Meridian OS targets operators and engineering managers managing hybrid human-AI teams. In terms of maturity, the repository is at an emerging stage (326 stars, 53 forks). The presence of a built-in simulation engine that operates without live backend runtimes indicates a functional prototype focused on UX concepts and governance interfaces.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:Avid

    Guide to Building a 'Company OS' and Agent Frameworks

    Avid shares an open-source AI agent framework and outlines the architecture of a 'Company OS' designed to orchestrate autonomous business agents using Kimi K3.

    8.6kbookmarks504.7kviews

    AI & LLMs· Tutorial

  • Repository:huangruiteng/loopx

    LoopX: Open-Source Control Plane for Long-Horizon AI Agents

    LoopX is a provider-neutral, local-first control plane for long-horizon AI agents. Designed to sit on top of harnesses like Claude Code, Cursor, and Codex, it provides persistent state, governance, and recovery across long-running tasks.

    5.6kstarsPython

    AI & LLMs· Tool

  • Repository:google/ax

    Google AX: Declarative Orchestration Runtime for AI Agents

    Google has open-sourced AX, a declarative orchestration runtime designed to manage autonomous AI agent workloads. Built on Kubernetes and Agent Substrate, it handles sandboxed execution, workspace pre-wiring, and network fencing at scale.

    6.2kstarsGo

    AI & LLMs· Tool

  • Repository:yc-software/qm

    QM: Multiplayer AI Agent Harness for Workplace Collaboration

    QM is an open-source agent harness designed for startups and teams. Unlike single-user personal assistants, it combines isolated personal workspaces with collaborative environments across Slack and the web.

    15.3kstarsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.