Open source · Apache-2.0 · v0.2.0

Continuous WorldQuant BRAIN research,
on your own machine

Hypothesis → review through a different provider → bounded simulation → real-result diagnosis → complementary signals → pre-submission acceptance. You control models, budgets, evidence and the queue — no chat window needs to stay online.

# pick one: pipx / Homebrew / DMG
$ pipx install wq-pilot
$ brew tap Octo-o-o-o/autowq && brew install wq-pilot

# any directory becomes your workspace
$ mkdir ~/autowq && cd ~/autowq
$ wq onboard

Install

Zero third-party dependencies, pure Python 3.11+ standard library. Four install paths; macOS users can add a menu-bar app.

①pipx (recommended)

One command, cross-platform: pipx install wq-pilot, then wq onboard in any empty directory.

②Homebrew

brew tap Octo-o-o-o/autowq && brew install wq-pilot; menu-bar app: brew install --cask Octo-o-o-o/autowq/worldquant.

③macOS DMG

Download the DMG from Releases, drag to Applications and double-click: the first-launch wizard picks a workspace, prepares the runtime and starts onboarding, then lives in your menu bar.

④Source (development)

git clone the repo, then ./wq onboard; tests: PYTHONPATH=src python3 -m unittest discover -s tests.

Note: onboarding never bypasses human steps — BRAIN registration/sign-in and vendor CLI logins are completed by you in the browser or terminal; the wizard only launches them and records their state. Models, APIs, automation and submission all start disabled.

How it works

A gated research pipeline: every step is auditable, every budget capped, every submission verified.

Hypothesize

The research-role model proposes candidate alphas from field evidence and full-history reviews; each task freezes its own routing snapshot.

Cross-provider review

The review role must run on a different provider, so one model's blind spots never confirm themselves.

Bounded simulation

Real simulations, GET polling and result accounting; uncertain POSTs are never blindly retried.

Diagnose real results

Failure-reason feedback, time-segment evidence and daily PnL correlations flow back into the next cycle.

Complementary signals

Bounded combination experiments with preregistered decay/neutralization variants, every result recorded.

Pre-submission acceptance

Per-candidate submission: research review, fresh platform checks, a single POST and verified acceptance status.

Features

Built for long unattended runs: budgets, authorization, recovery and dedup are defaults, not options.

Multi-provider orchestration

Grok Build, Devin, Cursor, ZCode, Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Qwen Code, OpenCode, plus standard OpenAI / Anthropic APIs.

Process isolation

sandbox-exec confines model processes on macOS; Docker images isolate them on Linux/WSL2; credentials live in a 0700 private directory.

Budgets & authorization gates

Single concurrency, per-provider budgets, authorization expiry, rate-limit handling; unknown costs are never booked as zero.

Crash recovery & dedup

A local SQLite ledger tracks every task; runs resume from the ledger and UNKNOWN requests require human reconciliation.

macOS menu-bar app

Cycle history, submitted alphas, routing presets, provider switches, intervals and system notifications — all from the menu bar.

Progress & export

Task progress with token/cost provenance; export summary/tasks/results (JSON/CSV) without cookies, passwords or task inputs.

Common commands

Run inside your workspace after install; every destructive capability starts disabled.

$ wq onboard --list            # detect host CLIs only; no writes
$ wq onboard                   # first-run wizard: providers, models, roles, login
$ wq doctor --fix-private      # environment checks, private-dir repair
$ wq autopilot status          # automation status
$ wq tasks                     # task queue
$ wq brain fields --datasets   # read-only data-field catalog snapshot
$ wq pause --reason "manual"   # pause queue and local model calls
PlatformInstallProcess isolation
macOSpipx / Homebrew / DMGsandbox-exec
Linuxpipx / sourceDocker images
WindowsWSL2 (same as Linux)Docker images

FAQ

Is autowq an official WorldQuant product?

No. autowq is an independent open-source project (Apache-2.0), not affiliated with WorldQuant. WorldQuant/BRAIN trademarks, platform and data belong to their owners.

Does autowq cost anything?

autowq itself is free and open source. It orchestrates your own model CLI subscriptions or API keys and your own BRAIN account — those costs are between you and the vendors. Onboarding never starts paid inference.

Do my credentials or research leave my machine?

No. Configuration, cookies, real alphas, databases, model outputs and logs stay local; exports exclude cookies, passwords, task inputs and evidence paths. Model requests go only to providers you explicitly select.

Is Windows supported?

Not natively. Use the WSL2 + Docker path; macOS and Linux are supported natively.

Does automated research mean automated submission and income?

No. Passing a screen, an accepted submission, consultant eligibility and actual payment are separate states. Research automation does not grant submission privileges; submission has its own acceptance gates.

Why must review run on a different provider?

A model reviewing its own hypotheses shares its own blind spots. autowq requires research and review roles to come from different providers for continuous automation, and the wizard enforces this at configuration time.