emisar

emisar is a self-hosted control plane that lets AI agents investigate and operate Linux servers through declared, policy-checked actions for ops teams.

What it is good for

  • Letting an AI agent check server status without shell access
  • Requiring human approval before risky server actions
  • Keeping an audit trail of what an AI agent ran on servers
  • Connecting AI assistants to infrastructure without a custom tool server

At a glance

Who it is for
Setup difficulty
Technical ยท Guided command-line setup

Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.

Cost
Not stated
Type
Agent app
Tasks
Works with
Claude, ChatGPT, Cursor, Codex, co:op

Momentum

Rank this week
Not ranked yet
Best rank
None yet
GitHub stars
376

GitHub numbers as of Nov 16, 2026. Updated weekly.

321 387 453 Oct 30, 2026 Nov 16, 2026
GitHub stars for emisar: 330 on Oct 30, 2026, 376 on Nov 16, 2026. Source: GitHub.

Questions

Do I need to know how to code to use emisar?
You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
What does emisar work with?
According to its own documentation, it works with Claude, ChatGPT, Cursor, Codex, and co:op.
What is emisar good for?
Letting an AI agent check server status without shell access, requiring human approval before risky server actions, keeping an audit trail of what an AI agent ran on servers, and connecting AI assistants to infrastructure without a custom tool server.

Similar agents to emisar

  • OpenMausBot

    OpenMausBot is an agent app that lets you chat with a team of AI bots, each with its own model, computer and apps, for people who want it local.

  • vapi-network

    vapi-network is a command-line client that lets AI agents find and pay for paid APIs in USDC on Base, with spending limits, for developers.

  • goose

    goose is an agent app that runs on your computer and handles coding, research, writing, and automation tasks for developers and power users.

  • OpenHuman

    OpenHuman is an agent app that runs AI agents on your desktop or a small server, using less memory and fewer tokens, for developers and power users.

  • cua

    cua is a toolkit that gives AI agents their own desktops, virtual machines and app-control tools for people who want agents to use computers.

  • qwen-code

    qwen-code is an agent app that writes, fixes, and explains code in your project from the terminal, editor, or desktop for developers.

Last updated Nov 16, 2026. Tracked since Oct 30, 2026. Parts of this summary required judgment because the source material was brief. Spotted an error? Tell us.