argusagent

Persistent, reviewed autonomy for research and engineering

Long-running agent work that can plan, execute, verify, pause, and continue beyond a single model turn.

Argus v0.1.6 · Source updates and packaged desktop previews are separate channels.

Website · Video Demo · Technical Report · arXiv:2608.05144 · WeChat Community · English / 简体中文

Manager → Planner → Engineer ⇄ Reviewer

---

[!IMPORTANT] Repository channels: microsoft/ArgusAgent is the official source repository; lbx154/Argus is the development preview. Changes reach the official repository through synchronization. Installing source from main is not the same as installing a published Desktop release.

In this repository, main is the stable source branch and dev is the development branch. Target development PRs at dev; promote reviewed, validated changes to main. See Contributing.

The Driver–Harness Model

A model is an engine: it burns compute and puts out tokens. A harness is the drivetrain that couples those tokens to files, shells, compilers, GPUs, and tests. The Driver is the seat — choosing what to do next, judging whether the last result was any good, and knowing when to stop and ask. In every other agent system that seat holds a human, which is why the work stops when they go to bed.

Argus takes the Driver's seat, splitting it across four roles deliberately not allowed to do each other's jobs:

	Owns	May not
Manager	Stage transitions, and where an admitted lesson is kept	Perform the work it is admitting
Planner	The next task, and the evidence it must produce	Move the campaign to the next stage
Engineer	Implementation, research, experiments, artifacts	Declare its own work complete
Reviewer	The verdict — correctness, evidence, limitations; may return blocked	Edit anything. It runs read-only

Credentials, payment, irreversible actions, and publication always stop for a human.

It also improves without retraining: admitted Skills and source-linked Wiki findings are scoped project → vertical → global by how far they were shown to hold, and new domains ship as verticals against a core that does not change — seven built in and seventeen more in the community package argus-verticals, with zero references to the authority boundary in any of them.

Because the worker cannot grade its own work, nobody has to watch it: across 27 campaigns and 1,548 hours it needed a human research decision about once every 310 hours, at 95–99% duty cycle. Everything else is in the technical report.

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

Argus-Pi (optional preview): We also maintain Argus-Pi, a lightly customized fork of Pi with small, Argus-focused improvements to task prompts, PDF reading, and execution/retry status reporting. It is available to try as a source preview; see the trial instructions. It is optional, and you can continue using any of the other supported backends. Argus remains the Driver for scheduling, role assignment, and task lifecycle; Argus-Pi focuses on the Harness for model and tool execution.

Ordinary Pi tasks can now learn project runtime tools: validate a reusable JSON transformation, use it in the current task, and retain its Skill and Wiki for later tasks under the existing task budget.

Harbor evaluation: Harbor Framework can invoke the complete bounded Argus Manager/Planner/Engineer/Reviewer runtime as a custom agent. See Harbor integration.

Coding-agent plugin: use the packaged MCP bridge and host-specific Skills without changing the core runtime. See Plugin quick start.

Counterexample research: use a live Counterexample Lab, an isolated Jacobian MCP bridge, and safe in-app source updates. See Counterexample Lab and Jacobian setup.

WeChat community

Scan the QR code to join Argus WeChat Group 2. Click the image to open it at full size. This code is valid before October 16, 2026, as shown in the image. After it expires, open an Issue and ask the maintainers for the latest code.

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
Cursor CLI	cursor	curl https://cursor.com/install -fsS | bash (Windows)	agent login or CURSOR_API_KEY
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

Separate Copilot account for Argus: run argus --setup --backend copilot --copilot-home "$HOME/.copilot-argus" --copilot-login. After setup succeeds and existing Argus processes are restarted, ordinary Argus launches use that account without changing the caller's login. See account binding, precedence and reset.

Research traces: Copilot sessions are preserved by default. Opt-in session reclamation and raw I/O rotation now archive verified copies before reclaiming online files; archives do not expire automatically. Review the effective policy in Settings and monitor disk space. See trace retention and export.

This optional trial assumes Argus is already installed. You also need Git, Node.js 22.19+ and npm. Argus-Pi is currently a source preview, not a separately published npm package or desktop installer. Installing the upstream Pi npm package does not install Argus-Pi.

1. Build a separate checkout in a new terminal. Run each command only after the previous one succeeds; do not overwrite your existing global Pi installation.

git clone --branch main https://github.com/Argus-AiTeam/Argus-Pi.git
cd Argus-Pi
npm ci --ignore-scripts
npm run hydrate:model-data
npm run build:offline
npm rebuild --workspace=@earendil-works/pi-coding-agent --ignore-scripts
node packages/coding-agent/dist/bundle/cli.js --version
node packages/coding-agent/dist/bundle/cli.js --list-models

The fork reuses Pi's existing authentication under ~/.pi/agent. If needed, run node packages/coding-agent/dist/bundle/cli.js, use /login, then exit. Choose a model your account can actually use, including its provider prefix. The model list alone is not a successful inference check; setup below runs a real turn. Never paste credentials into a task or issue. To isolate Pi's own configuration too, set PI_CODING_AGENT_DIR before login and throughout the trial.

2. Configure this trial terminal. Still at the checkout root, set the following process-local variables, replacing provider/model with your selected model. Remove any inherited per-role backend/model/runner overrides in this terminal; they can take precedence over the shared settings. Do not put these trial settings in your shell startup files or persistent system environment.

macOS / Linux:

export ARGUS_SKILL_HOME="$HOME/.argus-pi-preview"
export ARGUS_SKILL_RUNNER_BACKEND=pi
export ARGUS_SKILL_RUNNER_BIN="$PWD/node_modules/.bin/argus-pi"
export ARGUS_SKILL_MODEL="provider/model"
"$ARGUS_SKILL_RUNNER_BIN" --version
mkdir -p "$HOME/argus-pi-preview-workspace"
cd "$HOME/argus-pi-preview-workspace"
git init -q

Windows PowerShell:

$env:ARGUS_SKILL_HOME = "$HOME\.argus-pi-preview"
$env:ARGUS_SKILL_RUNNER_BACKEND = "pi"
$env:ARGUS_SKILL_RUNNER_BIN = (Resolve-Path ".\node_modules\.bin\argus-pi.cmd" -ErrorAction Stop).Path
$env:ARGUS_SKILL_MODEL = "provider/model"
& $env:ARGUS_SKILL_RUNNER_BIN --version
New-Item -ItemType Directory -Force "$HOME\argus-pi-preview-workspace" | Out-Null
Set-Location "$HOME\argus-pi-preview-workspace"
git init -q

Use a new, empty trial workspace, not a production project or the Argus-Pi checkout. The backend name remains pi; the explicit executable path selects the fork. The separate Argus state directory keeps trial configuration and missions apart from your normal installation. This is not a filesystem sandbox.

3. Verify, then launch. In that same terminal and workspace, run the following one at a time. Stop on any error; do not continue to the next command.

argus --setup --backend pi --non-interactive
argus --backend pi doctor --deep --advisor none
argus --config-help
argus

Check that ARGUS_SKILL_RUNNER_BIN points into your Argus-Pi checkout. Start with a small, reversible task confined to the trial workspace. Setup, deep diagnostics and tasks can consume your provider's quota or paid usage; "preview" does not mean free inference.

4. Stop and roll back. After leaving the UI, keep the trial terminal's environment and working directory and run:

argus --daemon-stop --drain
argus --status