Describe what to test. Let AI help to test the user flow.
Describe the goal and let AI operate the real app. FSQ records evidence and turns the exploration into a test you can review and replay.
An open-source project from FSQ Lab.
Quick start · 中文 · Guide · Contribute
See FSQ in action
https://github.com/user-attachments/assets/aa9d0a12-2f93-4894-8349-52a013424939
Watch the full demo on YouTube.
How it works
- Describe: You define the platform and target, goal, success criteria, and allowed and forbidden actions.
- Observe as AI tests the real UI flow and FSQ captures screenshots, interface state, events, and a reviewable test.
- Control what happens next: inspect the evidence and unchanged generated test, then separately approve any deterministic replay.
You get an evidence-backed result and a portable, reusable test you can review, keep, and replay without surrendering control.
Quick start
You need Python 3.11+ and the prerequisites for your platform and target. Choose one of the two paths below. Enter Provider credentials only in the FSQ UI—not in Coding Agent chat—and review the result and generated Case before separately approving any replay.
1. Coding Agent
Initial setup. Open your project in a Coding Agent and paste:
The official FSQ project is https://github.com/FSQ-lab/FSQ. Confirm the current project root with me. Following the official instructions, explain the Python-environment and project-file changes and get my approval, then install or upgrade the FSQ CLI and run
fsq init --agent skillin this project. Verify thatfsqworks and report where the Skill was installed. Next, ask me to openfsq uiand configure the FSQ LLM Provider and model in Settings; never ask me to put credentials in chat. Do not initialize a Workspace or run a test. When setup is complete, tell me to reload or start a new Coding Agent session, then stop.
Complete that reload before continuing.
First test. Copy this prompt into your Coding Agent:
Guide me through one FSQ test. Configure or select the Workspace, platform, and exact target with me. Confirm the Goal, observable success criteria, and allowed and forbidden actions. Keep credentials out of chat. Execute only after I approve. Report the result first, then show the exact returned Case unchanged. Do not replay it until I separately and explicitly approve replay.
Review the returned result and unchanged Case before deciding whether to approve replay separately.
2. FSQ UI
Initial setup.
python -m pip install --upgrade fsq-agent
fsq ui
In Settings, configure the FSQ LLM Provider and explicitly select a model.
First test.
- Create or select a Workspace, and configure its platform and target as needed.
- In Test Runner, select the exact target.
- Describe a verifiable result, review the test setup, and start the test. Review the result and Case before separately approving any replay.
Platforms
FSQ supports Web, Android, Windows, and macOS targets; see platform prerequisites, and help broaden support through contributions.
Documentation
- Getting started
- 中文快速开始
- CLI reference
- FSQ Case format
- Advanced Codex compatibility
- Platform prerequisites
- Support and stability
Built by FSQ Lab and the community
Built by FSQ Lab with thanks to all contributors. Want to help? Read CONTRIBUTING.md and join us.
License
MIT — Copyright (c) Microsoft Corporation.
1 maintainer
Metadata
1 maintainer
Release files for fsq-agent 0.1.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| fsq_agent-0.1.9.tar.gz | 11.5 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| fsq_agent-0.1.9-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 12.5 MB
Release files / fsq_agent-0.1.9.tar.gz
| Download URL | fsq_agent-0.1.9.tar.gz |
|---|---|
| Size | 11.5 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ea5d1c826fb19bae4394db3fce55582c55314f50cb03ab6a9589fb0b7e8df82c
|
|
BLAKE2b-256 checksum How to use checksums |
63f6992a33098b5c4cfd5350e15c3de8d34065ba9087cc54c831da1634ea8e01
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.13.1 {"installer":{"name":"uv","version":"0.13.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / fsq_agent-0.1.9-py3-none-any.whl
| Download URL | fsq_agent-0.1.9-py3-none-any.whl |
|---|---|
| Size | 953.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7607f6fd5145c9501344bb4d072aa327959adee1adc7cbc69d1a56236fe1e382
|
|
BLAKE2b-256 checksum How to use checksums |
e7bf3f694d70b8fdbb1236a785735d6f8311320803e3d3a1277394ae81eb76b0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.13.1 {"installer":{"name":"uv","version":"0.13.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for fsq-agent 0.1.9
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
