Item detail
github.com

ZJU-REAL/ClawGUI

ZJU-REAL/ClawGUI is a code repository in RepoRadar's AI tooling section, holding Gold tier and a 'try now' verdict. It is written primarily in Python. Its strongest signal is workflow potential, scored 9.6 out of 10.

Score8.5
Popularity100.0
Risklow
TierGold
Score breakdown
Usefulness8.3
Novelty8.5
Momentum8.0
Maturity9.1
Open-source/build8.4
Evidence7.2
Workflow potential9.6
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

ClawGUI ships a complete GUI-agent development stack instead of yet another isolated training script or evaluation harness. The five-module split (RL, Eval, Agent, Skills, APP) means you can take a single agent from training through evaluation to deployment without switching frameworks or rewriting glue code. The headline result -- 17.1 MobileWorld SR with a 2B parameter model trained end-to-end

Who should use it

Training GUI agents end-to-end with online RL on parallel Docker environments and real Android devices Evaluating GUI agents across 6 standardized benchmarks with 95.8% reproduction of official results Deploying GUI agents to control real mobile devices via natural language through 12+ chat platforms Building self-evolving skill packages with structured retrieval, failure diagnosis, restricted revision, and reuse On-device deployment of the full brain + GUI agent stack on a single Android phone (no desktop coordinator needed, powered by Shizuku) Reproducing the ClawGUI-2B 17.1 MobileWorld SR result with the released weights on HuggingFace and ModelScope

Who should skip it

Move on from ZJU-REAL/ClawGUI if the licensing terms, language support, or platform requirements do not fit your project.

About this signal

ZJU-REAL/ClawGUI is tracked by RepoRadar as a code repository in the AI tooling section. First seen 2026-07-12; the source record was last checked on 2026-07-12. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for ZJU-REAL/ClawGUI are workflow potential (9.6) and maturity (9.1), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The ZJU-REAL/ClawGUI record combines a 8.5/10 composite score with separate popularity (100.0), risk (low), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.

Risk explanation

Project was released 2026-04-13 (~3 months ago); the ecosystem around ClawGUI-2B is still building (1,310 stars is moderate for a research framework of this scope); Online RL training requires parallel Docker environments and real Android devices, which is a non-trivial infra footprint for individual researchers; Real-device deployment (ClawGUI-Agent + ClawGUI-APP) depends on Shizuku and ADB permissions; cloud deployment patterns are not yet documented; The 5-module split (RL / Eval / Agent / Skills / APP) means each module has its own release cadence and documentation; verify which modules you need before committing.

Evidence links
Closest alternatives / related signals
gui-agent online-rl mobileworld android ui-automation agent-training agent-evaluation agent-deployment
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-08-13T20:20:15Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

25 dated snapshots retained from 2026-07-12 through 2026-08-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.5 current · +0.0 net
Repository momentum5.8 current · -2.2 net
GitHub stars (observed)1,331 current · +20 net
GitHub stars1,331 exact observation
Versionclawgui-app-v0.3.1
Last release2026-05-21T17:06:26Z
Maintenancemaintained
Current risklow
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-138.55.81,331lowtry nowmaintained
2026-08-128.55.51,329lowtry nowmaintained
2026-08-118.55.51,329lowtry nowmaintained
2026-08-108.55.51,329lowtry nowmaintained
2026-08-098.55.51,329lowtry nowmaintained
2026-08-088.55.81,329lowtry nowmaintained
2026-08-078.55.01,322lowtry nowmaintained
2026-08-068.58.0Not recordedlowtry nownot recorded
2026-08-058.58.0Not recordedlowtry nownot recorded
2026-08-048.55.01,322lowtry nowmaintained
2026-08-038.55.01,322lowtry nowmaintained
2026-08-028.55.51,323lowtry nowmaintained

Why the record changed

stars changed

Stars changed: 1329 → 1331.

stars changed

Stars changed: 1322 → 1329.

stars changed

Stars changed: 1323 → 1322.

stars changed

Stars changed: 1320 → 1322.

stars changed

Stars changed: 1312 → 1320.

stars changed

Stars changed: 1311 → 1312.