Item detail
github.com

Skyvern-AI/skyvern

Skyvern-AI/skyvern is a developer tool in RepoRadar's Radar section, holding Gold tier and a 'try now' verdict. Its strongest signal is workflow potential, scored 9.4 out of 10.

Score8.3
Popularity88.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty7.0
Momentum9.0
Maturity8.3
Open-source/build8.4
Evidence7.2
Workflow potential9.4
Setup ease6.4

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

Why it matters

Useful for ops, RPA, and back-office automation teams that need to automate workflows on legacy web apps (no APIs, no selectors, just a browser) where traditional RPA (UiPath, Automation Anywhere) is too brittle and too expensive.

Who should use it

ops / RPA / back-office teams that need to automate workflows on legacy web apps (no APIs, no selectors, just a browser) logistics, insurance, and gov-tech teams running high-volume back-office browser work in production teams evaluating LLM-based browser automation as an alternative to traditional RPA (UiPath / Automation Anywhere) developers who need vision-driven clicks instead of brittle DOM selectors / XPath self-hosters who need to run browser automation on their own infrastructure (with the AGPL-3.0 caveat)

Who should skip it

Skip Skyvern-AI/skyvern if the source link, documentation, or setup requirements do not align with your current workflow or stack.

About this signal

Skyvern-AI/skyvern is tracked by RepoRadar as a developer tool in the Radar section. It was first seen on 2026-06-17 and last updated on 2026-06-17. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, Skyvern-AI/skyvern is strongest on workflow potential (9.4) and practical usefulness (9.0) and weakest on setup ease (6.4) — a profile worth weighing against your own priorities. This page summarizes the public evidence on the linked source page and states where additional review is still needed. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned Skyvern-AI/skyvern a composite score of 8.3 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 88.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

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

Risk explanation

AGPL-3.0 license: any modifications to a self-hosted instance that are exposed over a network must be open-sourced — acceptable for internal use, restrictive if you plan to resell as a SaaS; Headless browser automation consumes significant compute and depends on LLM API costs per run — benchmark on real workflows before scaling; Captcha / MFA flows require human-in-the-loop — factor in human review time for high-volume automation.

Evidence links
Closest alternatives / related signals
browser-automation rpa llm computer-vision vision-driven natural-language self-hosted managed-cloud
Verification record

What RepoRadar actually verified

Installed and tested

Hands-on setup or capability check retained by RepoRadar verification harness. Last checked 2026-07-13T03:23:10.254791Z.

partial · cohort-20260712-skyvern-import

Tester
RepoRadar automated local verification harness
Started
2026-07-13T03:23:08.662424Z
Completed
2026-07-13T03:23:10.254791Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
0 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Executed bounded check: Install and import Skyvern in an isolated Python environment.
  • Captured the complete sanitized stdout, stderr, exit status, and 1.59-second wall time.
Observed results
  • Command exited 0 after 1.59 seconds.
  • Expected marker 'CHECK_OK' was observed in retained output.
Observed strengths
  • skyvern==1.0.46 installed and imported successfully in the isolated Python environment without starting a browser, server, task, or provider.
Friction
  • The command emitted stderr; warnings or errors are preserved in the retained log for review.
Limitations
  • No browser, workflow server, task, credential, or model provider was started.
  • This bounded cohort check is not a production benchmark or a claim of real user-workflow adoption.

Pricing assessment: No paid plan or metered provider usage was exercised; package or licensing, hosting, and provider costs remain workflow-dependent.

Privacy assessment: No repository content, user data, or provider prompt was transmitted; broader product data handling was not assessed by this bounded run.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

38 dated snapshots retained from 2026-06-17 through 2026-08-03; 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 score8.3 current · +0.0 net
Repository momentum9.3 current · +0.3 net
GitHub stars (observed)22,659 current · +444 net
GitHub stars22,659 exact observation
Versionv1.0.47
Last release2026-07-16T21:38:30Z
Maintenanceactive
Current riskconditional
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
2026-08-038.39.322,659conditionaltry nowactive
2026-08-028.39.622,651conditionaltry nowactive
2026-08-018.39.022,640conditionaltry nowactive
2026-07-318.39.0Not recordedconditionaltry nownot recorded
2026-07-308.39.0Not recordedconditionaltry nownot recorded
2026-07-298.39.622,617conditionaltry nowactive
2026-07-288.39.022,604conditionaltry nowactive
2026-07-218.39.022,465conditionaltry nowactive
2026-07-208.39.022,465conditionaltry nowactive
2026-07-198.39.022,465conditionaltry nowactive
2026-07-188.39.022,465conditionaltry nowactive
2026-07-178.39.022,465conditionaltry nowactive

Why the record changed

stars changed

Stars changed: 22651 → 22659.

stars changed

Stars changed: 22640 → 22651.

stars changed

Source-observed stars changed: 22639 → 22640. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Stars changed: 22604 → 22617.

stars changed

Stars changed: 22465 → 22604.

stars changed

Source-observed stars changed: 22462 → 22465. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 22461 → 22462. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 22459 → 22461. This reports the retained observation delta and does not infer why the upstream change occurred.

version changed

Version changed: v1.0.46 → v1.0.47.

stars changed

Stars changed: 22215 → 22459.

verification changed

Verification changed: Discovered → Installed and tested.