Argus uses multimodal LLMs to test desktop apps, web UIs, and CLI tools with natural-language actions and deterministic assertions. Run lightweight tests locally, or move production testing into disposable isolated Capsules and distribute those Capsules through Fleet.
Running checkout.test.yaml ✓ Type 'hello from argus' into the editor ✓ text_visible: 'hello from argus' ✓ Open the File menu ✓ element_exists: Save 4 passed · 0 failed · production isolation available with Capsules
Adapters describe how Argus interacts with an application. Execution environments decide where that interaction is allowed to happen. Keeping those concerns separate is now part of Argus's core architecture.
Disposable VM execution for tests that should not share the operator's interactive host.
argus run failure pathsFast shared-host execution for development, quick checks, and systems without virtualization.
Natural language controls the exploratory parts; structured assertions and execution policy keep critical checks and boundaries explicit.
Describe what a user should do instead of maintaining brittle selectors for every UI interaction.
Assertions such as visible text, process state, exit code, URL, and page title are evaluated without asking the model to decide whether they passed.
Actions are normalized and checked against capabilities and host-safety policy before platform execution.
Supported desktop actions default to semantic UI Automation rather than intentional host-wide physical mouse/keyboard injection.
Run invasive tests inside dedicated VMs with secure guest control and explicit lifecycle ownership.
For supported scripted argus run failure paths, optionally retain disk/config evidence for forensic investigation without persisting live recovery credentials. Roam-triggered retention is not yet guaranteed.
Stage inputs and collect outputs through declared, bounded, hashed transfer authority rather than shared folders or clipboard shortcuts.
argus roam explores applications autonomously, records findings, and can build cross-session exploration memory.
Desktop GUI, browser, and CLI adapters share the same testing model while remaining distinct from execution placement.
Argus now treats placement, interaction, policy, and verification as separate concerns.
Use local mode for lightweight shared-host work or a Capsule for production isolation.
The selected execution environment allocates resources, stages authorized files where applicable, and creates the adapter inside that boundary.
The model receives supported observations, proposes an action, and Argus applies normalization/capability/policy checks before execution.
Structured assertions are evaluated deterministically against the current observation or adapter state.
Authorized artifacts are collected; supported scripted argus run failures may retain a forensic Capsule when configured; normal disposable sessions are torn down.
Adapters are not execution environments: they define how the target is controlled once an execution environment has been selected.
Windows UI Automation and Linux GUI support with screenshots/structured observations where available.
Playwright-powered browser testing with page observations and deterministic URL/title checks.
Execute commands and validate stdout, stderr, process state, and exit codes.
Argus keeps execution authority, evidence authority, and future read-only operations/monitoring as distinct trust boundaries.
Canonical ordered evidence, durable action dispatch, privacy controls, protected artifacts, transactional finalization, manifests/verification, derived reports, traceability, and approval/audit records.
Node identity/enrollment, authenticated heartbeats and capabilities, durable placement/fencing, remote Capsule execution, and canonical ATES transport above the existing ExecutionEnvironment → Capsule → Adapter boundary.
Scheduler/queue operations, matrix execution, timelines/indexes, and the separately authorized read-only Observer experience remain follow-on work; the site does not present them as shipped.
CI builds Windows x64/ARM64, macOS universal2, and Linux x86_64/ARM64 packages with checksums and GitHub build provenance.
Release binaries come from the same tagged source tree. Capsule execution still requires a configured virtualization host and prepared golden image.
x64 + ARM64
Portable ZIP Setup EXE MSI
Universal2 — Intel + Apple Silicon
Argus.app ZIP DMG
Currently ad-hoc signed; Developer ID signing/notarization is not configured yet.
x86_64 + ARM64
AppImage DEB RPM Arch .pkg.tar.zst
pip install argus-app-testing
pip install "argus-app-testing[browser]" playwright install chromium
pip install "argus-app-testing[all]"
# Local model example ollama pull gemma3:9b # Initialize and run argus init argus providers argus run
For production Capsule setup, start with the documentation hub.
Use Argus locally for fast development, isolate invasive work in Capsules, and distribute Capsule execution through Fleet while ATES preserves the canonical evidence trail.