microsoft/ArgusAgent

microsoft/ArgusAgent

Description: A persistent, reviewed multi-agent runtime for long-horizon research and engineering.

Language: Python

License: MIT

Stars: 8

Forks: 1

Open issues: 0

Created: 2026-08-05T02:20:20Z

Pushed: 2026-08-20T06:53:41Z

Default branch: main

Fork: no

Archived: no

README:

---

> [!IMPORTANT] > Repository status: This is the official Argus release repository. Preview > updates are published at > [lbx154/Argus](https://github.com/lbx154/Argus). Updates are synchronized > between both repositories; Watch or Star either repository to follow the > project.

What is Argus?

Most agents are optimized for one conversation or one coding turn. Argus is built for work that lasts: it keeps state, separates execution from judgment, and resumes from verified progress instead of starting over.

| Capability | What it means | |---|---| | Persistent state | Tasks, checkpoints, decisions, Skills, and evidence survive sessions and runtime upgrades. | | Independent review | Execution and verification stay separate; normal rounds end with a Reviewer judgment. | | Four-role runtime | Manager, Planner, Engineer, and Reviewer have distinct authority and responsibilities. | | Real tool use | Agents work through files, terminals, experiments, APIs, and inspectable artifacts. | | Domain extensibility | Verticals can define custom stages, tools, evidence requirements, and completion standards. | | Multiple backends | Run with GitHub Copilot CLI, Pi, Codex CLI, Claude Code, OpenCode, Grok Build, Qoder, or DeepSeek Harness. |

Runtime model

| | Authority | Responsibility | |---:|---|---| | 01 | Manager · Control | Interprets operator intent, selects the workflow, and owns stage transitions. | | 02 | Planner · Direction | Chooses the next high-value task and defines the evidence it must produce. | | 03 | Engineer · Execution | Implements, researches, runs experiments, and creates inspectable artifacts. | | 04 | Reviewer · Verification | Independently checks correctness, evidence, limitations, and completion. |

A project can stop, resume, survive a runtime replacement, and continue from its latest verified position.

Native backends: GitHub Copilot CLI · Pi · OpenAI Codex CLI · Claude Code · OpenCode · Grok Build · Qoder · DeepSeek Harness

Harbor evaluation: Harbor Framework can invoke the complete bounded Argus Manager/Planner/Engineer/Reviewer runtime as a custom agent. See [Harbor integration](https://github.com/lbx154/Argus/blob/main/docs/harbor.md).

Coding-agent plugin: use the packaged MCP bridge and host-specific Skills without changing the core runtime. See [Plugin quick start](https://github.com/lbx154/Argus/blob/main/docs/plugin.md).

Quick Install

Choose the section for your operating system. Do not mix commands between platforms. All platforms need Node.js 22.12+ from nodejs.org and one authenticated Agent CLI. Reuse the CLI you already work in; Argus does not require a separate account. Docker is not required for a normal Argus installation; it is only an optional prerequisite for the separate Harbor evaluation integration.

> [!TIP] > Recommended: let the Code Agent you already use install and verify Argus. > Copy the prompt in the Agent-assisted section below. The manual commands remain > available for users who prefer to install each step themselves.

| Agent CLI | Backend | Install | Authenticate | |---|---|---|---| | GitHub Copilot CLI | copilot | npm install -g @github/copilot | copilot login | | OpenAI Codex CLI | codex | npm install -g @openai/codex@latest | codex login | | Claude Code | claude | npm install -g @anthropic-ai/claude-code | Run claude, then /login | | Pi | pi | npm install -g --ignore-scripts @earendil-works/pi-coding-agent | Run pi, then /login | | OpenCode | opencode | Official install | opencode auth login | | Grok Build | grok | Official install | grok login | | Qoder CLI | qoder | npm install -g @qoder-ai/qodercli | qodercli login | | DeepSeek Harness | dsh | npm install -g @deepseek-ai/dsh | Configure DEEPSEEK_API_KEY or the dsh Models page |

The public preview is installed directly from the current GitHub archive until the first PyPI release is published.

Recommended: Agent-assisted installation

Send this prompt to an already installed Code Agent:

Read https://github.com/lbx154/Argus/blob/main/docs/agent-install.md and install
Argus using the section for this operating system. Prefer the Agent CLI running
this conversation as the Argus backend. Do not create a venv on Windows or
macOS; keep the documented venv on Linux. Run setup through its real Agent-turn
smoke test, then run `argus doctor --deep --advisor auto`. Before account login,
sudo, or global configuration changes, explain why and wait for approval. Never
ask me to paste a password, token, or API key into the conversation.

The agent follows the [installation execution contract](https://github.com/lbx154/Argus/blob/main/docs/agent-install.md).

Windows 10/11 — direct pip, no virtual environment

Install Python 3.11+ from python.org and select Add Python to PATH in the installer. Then open a new PowerShell:

py --version
node --version
py -m pip install --upgrade pip
py -m pip install --upgrade --force-reinstall "argus-skill @ https://github.com/microsoft/ArgusAgent/archive/refs/heads/main.zip"
$Scripts = py -c "import sysconfig; print(sysconfig.get_path('scripts'))"
$Argus = Join-Path $Scripts "argus.exe"
if (-not (Test-Path $Argus)) { throw "Argus entry point not found at $Argus" }
$env:Path = "$Scripts;$env:Path"
& $Argus --version
& $Argus --setup
& $Argus doctor --deep --advisor auto
& $Argus --status
& $Argus

Calling $Argus proves setup is not accidentally using another stale installation. $env:Path also makes plain argus available in the current PowerShell. The troubleshooting section covers persistent PATH repair.

argus doctor is an active repair command. By default it launches an installed Agent CLI in the real Argus directories with tools enabled, lets the Agent inspect and fix the machine, then reruns deterministic checks. Use argus doctor --advisor none --verify for a no-model verification. The active repair may...